Artificial Intelligence Evaluation

Organizations deploying AI face two fundamental governance challenges: managing AI risk and sustaining AI value. Both depend on evidence whose sufficiency cannot be taken for granted. We call the shared underlying challenge the AI Evaluability Gap: the condition in which organizations lack sufficient evidence to support high-confidence governance decisions regarding either risk or value. We argue that this gap reflects a category error in current practice. Existing governance approaches focus primarily on properties of systems, such as safety, fairness, reliability, compliance, and value, while paying comparatively little attention to the evidentiary foundations required to justify decisions about those properties. We further argue that AI governance encompasses both operational decisions regarding whether a system may operate and investment decisions regarding whether it merits continued organizational resources. To address this problem, we introduce Evaluability, defined as the capability of a system to generate, maintain, and renew evidence sufficient to support high-confidence governance decisions over time. We formalize governance decisions as functions of calibrated confidence Conf(D|E) and identify six properties of evaluable evidence: observability, attributability, intervenability, verifiability, calibration, and temporal validity. The framework distinguishes Operational Certification, which relies primarily on structural evidence to justify deployment decisions, from Investment Certification, which relies primarily on causal evidence to justify continued resource allocation. We argue that evidence sufficiency is a missing layer of AI governance and that closing the AI Evaluability Gap is a prerequisite for both managing risk and sustaining value in AI-enabled organizations.

Trust in the application of generative Artificial Intelligence (AI) relies on well-governed measurable evidence of performance and safety. In practice, however, evaluation data is often fragmented across systems, inconsistently structured and difficult to compare. We introduce the Generative Responsible AI Data Evaluation Schema (GRAIDES) as a lightweight open-source data model for centralising AI observability across popular vendors. Practical blueprints for code, architecture and statistical evaluation are shared as guidance about how to approach generative system assurance at the organisational level. Illustrative case study results are reported from Westminster City Council's AI catalogue with a focus on measuring human-model alignment including detecting systematic disagreement between evaluators. By framing evaluations as a data modelling problem, GRAIDES provides a practical pathway toward more consistent and reproducible benchmarking, tuning and assurance activities for generative AI systems.

AI-native course assessments in senior computer science courses and related fields should grade students by \emph{AI-resilient skill}: the ability to achieve outcomes beyond a strong AI baseline. Such assessments should allow students to use AI freely, while reducing the extent to which greater private AI budget or more intensive AI use, by itself, becomes a grading advantage. This paper proposes a minimal formal framework for this goal. The framework specifies a real task, an executable evaluator, a declared AI-native Pareto frontier, and a grading rule based on Pareto surplus. The central claim is simple: Pareto surplus provides a measurable, protocol-relative certificate that a submitted artifact achieves a tradeoff not already supplied by the declared AI baseline, and grading by this surplus is AI-resilient with respect to that baseline. Interpreting surplus as evidence of student skill requires the surrounding assessment protocol--for example, design reports, ablations, prompt traces, oral checks, or reproducibility explanations--but the grading certificate itself is behavioral and executable. The framework is then extended to practical complications, including self-improving AI loops, budget neutrality, server-mediated feedback, and prompt-based red teaming. As a concrete instantiation, we describe an AI-resilient approximate-membership assignment centered on Bloom filters for COMP 480/580 at Rice University, designed to test whether students can improve beyond AI-generated implementations.

Reasoning models are increasingly used in settings where the final answer is not the only object of review: educational tools may show students intermediate steps, decision-support systems may require human oversight, and audit workflows may inspect traces for misleading or biased input. In such settings, two responses can receive the same final-answer score while differing in whether the trace explicitly flags injected biasing content. Accuracy-only evaluation collapses these cases. We study this gap as a measurement blind spot for responsible evaluation and introduce a minimal trace-level diagnostic with two axes: \emph{susceptibility} (whether the bias breaks a previously correct answer) and \emph{acknowledgment} (whether the trace contains a rubric-defined surface reference to the injected content). Across thousands of biased GSM8K trials, GPT-4o and Claude Sonnet~4 have similar susceptibility rates ($1.3\%$ vs. $1.2\%$) but substantially different acknowledgment rates ($13.0\%$ vs. $75.0\%$) under the same rubric.

AI evaluations are widely used for testing and understanding progress. However, the diverse evaluators bring with them inconsistencies that challenge analysis and comparison. First, results are saved in incompatible formats, scattered across leaderboards, papers, blog posts, evaluation harness logs, and custom repositories. Second, results are created by different evaluation frameworks, which produce divergent scores for nominally identical evaluations and record metadata inconsistently, hindering comparison, cross-community evaluation science, cost reduction, and reuse. We introduce Every Eval Ever, the first shared schema and community-crowdsourced repository for AI evaluation results. The schema standardizes how evaluations are represented in a unified, single JSON document. It is source-agnostic by design, ingesting results from evaluation harnesses and papers alike, and optionally stores per-instance outputs for fine-grained analysis. We contribute: (i) a community-governed metadata schema with a companion instance-level schema, the first standardization effort of its kind; (ii) automatic converters from popular formats, evaluation harnesses, and leaderboards to the unified schema; and (iii) a crowdsourced community database hosted on Hugging Face, currently spanning to date 22,235 models, 2,273 unique benchmarks, and 31 evaluation formats.

AI evaluation results are produced at scale but reported inconsistently across leaderboards, model cards, benchmark papers, and company blogs. The cost is interpretive: readers cannot reliably compare results across sources, identify what a report omits, or trace an aggregate claim to its underlying evidence. Recent efforts address isolated components but leave three gaps: they cover only narrow slices of the evaluation lifecycle and do not compose into a single interpretable record; they specify static representations that do not differentiate the questions different stakeholders bring to the same evidence; and they remain proposals on paper, lacking the extraction infrastructure required for adoption at scale. We present \EvalCards{}, an operational reporting layer that composes benchmark metadata, evaluation run data, and model metadata into a unified record. We (1) derive a reporting schema from a structured review of 52 papers and 10 stakeholder interviews, (2) implement four interpretive signals (reproducibility, documentation completeness, provenance and risk, and score comparability), rendered through reader modes calibrated to research and non-research audiences, and (3) deploy a monitoring tool that applies \EvalCards{} across 5,816 models, 635 benchmarks, and 101,843 results, surfacing systematic gaps in current reporting practice.

AI Scientist agents are often evaluated as if capability were mainly a function of model quality, prompting, or reasoning scaffolds. We test a different hypothesis in drug-asset valuation: for knowledge-intensive scientific decisions, the limiting factor is often the evidence substrate the agent can access. We run a controlled three-arm ablation on a production valuation agent: A is a plain web-only LLM analyst, B adds public structured tools plus a 14-dimension valuation playbook, verifier, objectivity policy and red-team, and C adds the proprietary Noah AI corpus of curated pipeline, trial and deal intelligence. Across a 13-asset stratified benchmark, B improves calibration and audit discipline: tier-in-range accuracy rises from 0.80 to 0.89 and objectivity from 3.16 to 3.30. But B does not remove the factual ceiling. Under capability-superset accounting, A and B recover only 0.25 and 0.38 of the curated gold competitive record, while C recovers 0.96; on the curated long-tail subset, C reaches 0.93 vs. 0.26/0.30. Raw blind-panel decision quality is similar for A and B (7.01 vs. 6.96), so we introduce completeness-aware decision utility: informed decision-quality = decision-quality x gold-coverage. On this metric, C reaches 7.43 vs. 1.76/2.57 for A/B. Even a perfect non-proprietary-data report would be capped at 3.83 by B's coverage. The result is not that reasoning scaffolds are unimportant; they improve calibration and discipline. Rather, proprietary evidence sets the upper bound of what the AI Scientist can know and therefore decide.

We study the problem of auditing a black-box algorithmic decision-maker from observable inputs and outputs alone. Our main result is an exact decomposition: under precisely characterized conditions, the cumulative \emph{regret} of a dynamic policy equals the sum of per-period covariances between the cost vector and the policy's decision. This extends the single-period identity of Aldridge~(2026) to the full multi-period setting of stochastic dynamic programming. We prove the identity holds exactly under i.i.d. costs and mean-unbiased Markov policies, derive closed-form bias corrections for non-stationary and time-varying cases, and establish the discounted-horizon analog. A Bellman recursion for the covariance regret functional connects the result to standard reinforcement learning algorithms; for rolling-window policies, the estimation-error bias is $O(d/w)$. The decomposition has direct implications for algorithmic auditing in strategic environments: in platform mechanism design, it provides a welfare-based audit metric without access to the agent's private type; in repeated games, covariance reduction is a sufficient condition for policy improvement; in procurement and ad auctions, the bias correction quantifies welfare loss from strategic misreporting. The associated trajectory estimator is consistent, asymptotically normal with HAC variance, and computable in $O(T \cdot nd)$ time. This makes the proposed approach a tractable, model-free audit tool for platform mechanisms, algorithmic portfolio strategies, and any sequential decision system subject to external performance review.

Current AI models frequently exhibit epistemic sycophancy, endorsing claims to agree with a user. Existing evaluations typically measure this either by assessing what it takes to make a model shift a binary endorsement or by eliciting an explicit probability in a proposition. However, much user-facing sycophantic behavior is demonstrated through shifts in graded support expressed through ordinary language. We propose the AI Epistemic Deference Index (AEDI): a continuous, unidimensional score representing how sensitive the support expressed in a model's output is to the attitude expressed in a user's prompt. To generate AEDI, we provide a new protocol for estimating probabilities from natural language outputs, using LLMs-as-judges validated for consistency and correlation to human judgment. We deploy it on a new curated database of 500 propositions across diverse topics and 16,000 prompts varying in user attitude, testing eight prominent models. Every model exhibits substantial deference, though with large and systematic differences across providers, with Claude models demonstrating the least, and Grok and Gemini models the most. The effect is amplified in prompts requesting a written artifact, and concentrated on propositions where models hold weaker priors. We release AEDI as an easy-to-update benchmark and measurement pipeline for output-level sycophancy evaluation.

Appropriate reliance on AI advice has become a central research theme in human-AI collaboration. Existing frameworks have focused exclusively on point predictions as AI advice. However, set-valued AI advice (e.g., discrete sets or continuous intervals) is increasingly being used to communicate uncertainty and improve human decision making. In this paper, we develop the first formal framework for measuring appropriate reliance on set-valued AI advice within the sequential judge-advisor paradigm, spanning both classification and regression tasks. For classification, we first introduce the dimensions that are necessary for evaluating set-valued AI advice. We then define two metrics: correct reliance rate on AI and correct reliance rate on self, which jointly characterize appropriate reliance in this setting. For regression, we introduce quantity of AI reliance and quality of AI reliance, which respectively measure whether a decision maker utilized the AI advice and whether their reliance helped them get closer to the ground truth relative to their initial estimate. Through the application of our framework, we demonstrate how these metrics capture important nuances in human-AI collaboration that existing measures overlook.

Generative AI makes answers easy and understanding hard, and uncritical use invites cognitive offloading. Schools still measure unaided performance, yet the real task is to produce good work with AI: framing an ill-defined task, judging the output, and steering the model toward a better result. This ability is rarely assessed in its own right; where measured, it collapses into one "prompting" score that cannot diagnose why AI use succeeds or fails. We propose CoRe-3 (Co-Reasoning), a competency model factoring productive AI use into three assessable skills we abbreviate FJS: Framing (specifying an ill-defined task before invoking AI), Judging (evaluating output for errors and unstated assumptions), and Steering (iteratively redirecting the model). Its distinguishing claim is the separation of pre-generation Framing from post-generation Steering, with Judging as the gate between. We ground the skills in theory, state five testable propositions, and instantiate them in CoReasoningLab, an open platform that presents flawed AI output and scores them independently. Over simulated learners (generated and graded by different models), the skills dissociate: each tracks its own manipulated competence while staying flat in the others, and grades become correlated when one competence is shared across all three (convergent and discriminant validity), across grader backends from two providers. Human-rater agreement and outcomes are next; we release the instrument, data, and protocol.

Clinical AI evaluation increasingly delegates scoring to large language models (LLMs) acting as AI raters, yet their scoring behavior across evaluation conditions has not been quantitatively characterized. We address this gap through a factorial study of AI rater behavior in adult type 2 diabetes (T2D) pharmacotherapy at 12-month outpatient follow-up, a clinical task involving complex decision-making operationalized across seven evaluation questions. Four open-source LLMs served simultaneously as clinical decision support system (CDSS) models and AI raters. Each CDSS output was scored under two scoring protocols: a rubric-anchored Gold Rubric (GR) protocol incorporating a patient-specific rubric, and a rubric-free Non Gold Rubric (Non-GR) protocol. Linear mixed effects models crossed the scoring protocol factor with five design factors -- CDSS model, CDSS prompt configuration (document-referenced generation [DRG] vs.\ Baseline), rater model, prompt character, and prompt type -- and estimated main effects together with their protocol interactions. Across all questions, AI raters yielded consistently higher scores within a very narrow range (74--78 points on average) under Non-GR compared to those under GR (7.69 to 49.64 points lower mean scores; 1.68 to 3.67 times wider interquartile ranges). Within each question, GR amplified the AI rater's discrimination between DRG and Baseline CDSS outputs by factors of 1.76 to 5.10, while also revealing substantial behavioral variation across rater models that Non-GR suppressed. These findings support rubric anchoring as the scoring protocol that preserves discriminative power in clinical AI evaluation; rubric-free scoring cannot substitute when questions require patient-specific or jurisdiction-specific criteria that rater models cannot infer from parametric knowledge alone.

Safe global deployment of AI models requires alignment with human values that vary across cultures. Yet rater pools in safety evaluation datasets remain largely geographically homogeneous, failing to capture geo-cultural differences. Further, it remains unclear whether such differences persist after controlling for demographics such as age, gender, and ethnicity. Through a meta-analysis of safety datasets, we find that most do not report geo-cultural information, and those that do lack a unified methodology to jointly analyze geo-cultural and demographic correlates. Using the Inglehart-Welzel dimensions of cross-cultural variation, we demonstrate via multilevel modeling that cultural zone membership explains variance in safety ratings beyond standard demographics (p<0.05 across 6 datasets). Moreover, our analysis indicates that roughly 10% of items in the datasets we examined are culturally sensitive: likely to be misclassified as safe without adequate cultural representation. We evaluate LLMs as both rater surrogates and triage tools, finding that current LLMs do not reliably stand in for raters, though they can help prioritize culturally sensitive items for human annotation. Our findings motivate more culturally pluralistic safety evaluation and offer practical takeaways to support it.

Current alignment paradigms for generative artificial intelligence rely predominantly on monolithic benchmarking frameworks that reduce the plurality of human judgment to aggregated statistical baselines, thereby obscuring cultural, demographic, and contextual variability in evaluation. We introduce a state-space constrained emulation framework for AI evaluation that replaces singular assessment functions with a structured manifold of synthetic cognitive profiles representing diverse human perspectives. We show that modern generative architectures can instantiate and maintain these evaluative personas with high consistency, enabling a form of pluralistic, perspective-dependent benchmarking that more closely reflects real-world consensus variability. However, we further analyze the stability of these simulated evaluators under sequential inference and stochastic prompt perturbations, revealing systematic degradation in persona coherence that manifests as state-space drift and semantic inconsistency. These findings suggest that static alignment constraints are insufficient for sustaining robust evaluative behavior over time. Instead, we argue for the necessity of embedding dynamic, viability-driven regulatory mechanisms within generative systems to preserve coherent cognitive emulation. By framing persona-based evaluation as a structured dynamical system over latent representation manifolds, this study provides a foundation for more adaptive, human-aligned, and context-sensitive approaches to AI evaluation.

Two clinical AI systems can score nearly identically on coverage-based rubrics yet behave radically differently when their patient inputs change: one updates its recommendations to match the new clinical signal, while the other produces the same output regardless. We introduce the Causal Sensitivity Score (CSS), a pre-registered interventional metric that mutates oncology tumor-board cases along five clinically meaningful dimensions - biomarker flips, prior-treatment failures, biomarker removals, surgery-status changes, and stage perturbations - and scores whether each model updates its recommendations in the pre-registered correct direction using a {0, 0.5, 1.0} scale. Benchmarked against the Consensus Match Score (CMS), a coverage-based weighted recall metric, six frontier models from three labs evaluated in single-shot inference across 224 cases rank in nearly opposite orders: all six models change rank, the CMS-worst model becomes CSS-best, and one upper-mid CMS model ranks last on CSS. We further surface a universal safety blind spot: every frontier model fails on surgery-status interventions (at most 17.2% CSS on Family D), a finding CMS does not expose. The metric also transfers to tool-using agents: in a ReAct-style experiment, tool use improves CSS for five of six models (+2.5 to +20.3 percentage points), yet the lowest-CSS model retrieves the same chart sections and still fails to update its recommendations - revealing a structural responsiveness deficit visible only under counterfactual evaluation. Cross-judge replication and three-rater medical-professional validation confirm the aggregate findings. Interventional pre-registered metrics like CSS complement coverage-based evaluation for clinical AI agents: they capture responsiveness that coverage metrics miss and offer a candidate dense reward signal for future agentic RL systems.

Many applications require statistically valid inference across many related tasks, while using only a handful of high-quality labels per hypothesis. In AI evaluation, these tasks may correspond to model behaviors across prompts, subgroups, or hypotheses; in social science surveys, they may correspond to related questions, populations, or measurement conditions. Prediction-powered inference (PPI) uses abundant but inexpensive proxy measurements to improve inference from limited, ground-truth labels, but commonly used methods treat tasks independently and therefore fail to exploit shared structure across related tasks. This limitation is especially important in settings where only a small number of labels are available per task. To address this issue, we introduce a multi-task prediction-powered inference framework that uses labeled data from related tasks to improve power while preserving task-specific inference. Our methods exploit the shared structure in the proxy-ground-truth relationship through cross-task recalibration, while retaining within-task rectification and power tuning to construct accurate point estimates and confidence intervals. We prove that efficiency gains beyond power-tuned PPI are only possible when the proxy-ground-truth relationship contains nonlinear structure; affine cross-task recalibrations are asymptotically equivalent to using the original proxy. We complement our theoretical findings with experiments on synthetic and semi-synthetic datasets, as well as a case study auditing language models on election-related information during the 2024 U.S. presidential election. Using a large human-annotation study, we show that cross-task recalibration can substantially reduce confidence interval widths when labels are scarce.

AI tools to support real world decision making must be able to build simulation models that inform their recommendations and render them interpretable. Tools that can automate aspects of modeling practice must complement human expertise, not replace it. The BEAMS Initiative aims to guide the development of AI tools for modeling and simulation toward forms that are responsible and ethical by establishing benchmarks for human centered modeling and simulation practices. The initiative uses open digital and organizational infrastructure to collaboratively evaluate AI tools for modeling and simulation. The open source sd ai project hosted by the initiative establishes transparency and enables contributions to be shared broadly. A steering group focuses on prioritizing potential benchmarks, while a technical group focuses on implementing the benchmarks in the form of automated tests. Tests for several distinct categories of evaluation have been implemented and applied to AI tools that support qualitative model building, quantitative model building, and model discussion. These include tests for causal translation, model iteration, causal reasoning, conformance, model behavior explanation, suggested model building steps, and suggested model fixes. When engines from the sd ai project are coupled with different LLMs, their performance on these evaluations reveals variability across different AI tools. The evaluations implemented by the initiative demonstrate that AI enabled modeling tools perform better at discussion and basic qualitative tasks than with causal reasoning and quantitative error fixing. No single LLM dominates across engine types, highlighting the importance of specific tasks and tradeoffs between speed and accuracy. Ongoing efforts of the initiative aim to incorporate benchmarks that address concerns about bias by considering alternative perspectives and human centered use cases.

The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings. Prior work has identified test-time contextual cues, such as hypothetical scenarios, as a source of verbalized evaluation awareness and subsequent behavioral shift. In this paper, we investigate a potential explanation of this phenomenon: evaluation meta-knowledge, defined as parametric knowledge about the structural traits that characterize evaluations. Similar to dataset contamination, where benchmark exposure leads to higher performance through memorization, we hypothesize that models trained on texts describing evaluation practices may implicitly learn to recognize and respond to evaluation-like contexts, for instance, through exposure to scientific articles or social media posts about AI benchmarking. To test this, we fine-tune models on synthetic documents describing evaluation traits such as verifiable structures or harmful requests. Evaluating this fine-tuned model on five safety benchmarks, we find that it is significantly safer than the base model and control model. This behavioral shift persists even when restricting the analysis to responses lacking explicit verbalization of evaluation awareness. Our results demonstrate that evaluation meta-knowledge may inflate safety benchmark performance, introducing a novel confounder that is independent of explicit memorization or verbalized evaluation awareness, thus, challenging to detect. These findings have important implications for the design and interpretation of AI safety evaluations. Our code and models are available at https://github.com/compass-group-tue/arxiv2026_evaluation_meta_knowledge.

Existing AI evaluation practices often fail to capture how systems actually perform in low-resource environments, where operational constraints shape usability as much as model quality. Through a structured analysis of existing benchmark families across speech, chat/RAG, and vision systems, we identify critical gaps between laboratory evaluation practices and real-world deployment conditions in low-resource environments. We argue that the meaningful unit of assessment is the deployed system rather than an isolated model and that effective evaluation frameworks must integrate task performance with deployment conditions such as noisy inputs, code-switching, intermittent connectivity, low-end hardware, and domain shift. At the same time, benchmarks should recognize that different application classes require distinct evaluation profiles rather than a single aggregate score that obscures operational differences. To support practical decision-making, we propose a shared reporting framework that preserves comparability across systems and application types while remaining sensitive to deployment context. Finally, we emphasize the need for concise and actionable reporting artifacts for policymakers, donors, and implementers, including standardized one-page benchmark cards, deployment profiles, and explicit documentation of failure handling procedures and human oversight mechanisms.

This paper examines how estimates of AI use in scientific writing can be biased when evaluation methods ignore contextual differences across countries and fields. Using large-scale data on journal publications from Dimensions, we construct AI-likeness benchmarks based on differences between human-written and LLM-rephrased abstracts. We show that a pooled benchmark may confound pre-existing stylistic variation with AI-generated text, producing substantial distortions across country-field groups even in pre-LLM publications. In contrast, country-field-specific benchmarks attenuate such distortions and provide a more credible baseline for comparison. Applying these methods to publications in 2025 reveals that the pooled benchmark systematically overestimates AI use in certain countries and fields while underestimating it in others. These findings highlight the importance of context-aware measurement for accurate and equitable evaluation of AI use in science.

Evaluating generative AI (GenAI) systems is challenging because many targets of evaluation are broad, contested concepts, such as "reasoning," "fairness," or "creativity." When these concepts are left underspecified, it becomes unclear what should be measured or how evaluation results should be interpreted. This problem reflects a missing step: systematization, that is, moving from a broad background concept to an explicit, structured account of the concept in measurable terms. To help address the fact that systematization is cognitively demanding and resource-intensive, we investigate whether AI assistance can support this process. To enable AI-assisted systematization and assess its quality, we introduce a structured representation of a systematized concept, a concept spec, and a validation worksheet. We then develop two AI-assisted systematizers: a direct, zero-shot approach and a multi-agent approach that more closely mirrors manual systematization approaches from existing literature. We use these systematizers to produce concept specs for two concepts -- hate-based rhetoric and digital empathy -- and evaluate resulting concept specs on content validity and information recoverability.

Security evaluations inherently depend on stable identifiers. Any finding, audit, or regulatory decision must remain attached to the specific artifact it pertains to. Continuously updated artificial intelligence systems violate this core assumption, with public model designations remaining static while underlying weights, prompts, retrieval mechanisms, misuse classifiers, inference settings, and serving infrastructures undergo unannounced modifications. Consequently, current evaluations frequently apply to superficial labels rather than identifiable and distinct systems. To resolve this, we propose referential security as a new paradigm for AI evaluation. The fundamental security question extends beyond whether a model is safe to whether subsequent parties can conclusively determine which system a specific safety claim addressed. This approach reframes model identity as an empirically verifiable property and separates referential stability from the substantive security claims it conditions. This framework brings tractability to three critical workflows that current practices handle poorly. Specifically, it enables reproducible evaluation, longitudinal audit validity, and cross-provider equivalence. By grounding these evaluations in verifiable artifacts, our approach ensures that safety audits and regulatory findings maintain their empirical utility across the operational lifecycle of dynamic systems.

This article is the rejoinder to ``The ICML 2023 Ranking Experiment: Examining Author Self-Assessment in ML/AI Peer Review,'' to appear in the Journal of the American Statistical Association with discussion. To address the practical and theoretical points raised by the discussants, we organize our response around four core themes: (i) formulating peer review as a statistical estimation problem; (ii) mitigating equity and strategic concerns in the deployment of the Isotonic Mechanism; (iii) incorporating complementary signals such as reviewer rankings and structured metadata; and (iv) exploring a human-centered framework for peer review in the era of generative AI.

Current approaches to AI compliance treat conformity as a binary, audit-time verdict rather than a continuous, measurable property of production systems. We argue that this compliance fiction is structurally ill-suited to the requirements of the EU AI Act, which demands ongoing human oversight and the detection of emergent behavioural drift in deployed systems. We introduce governance from metrics, a principle whereby regulatory compliance is derived as a continuous signal from runtime observability rather than from static assessments. Building on this principle, we present govllm, an open-source framework implementing a governance-driven routing architecture in which model selection is determined by accumulated compliance scores rather than by latency or cost alone. Central to our approach is a panel of regulatory judges - LLM evaluators specialised per criterion (EU AI Act, GDPR, ANSSI, accessibility) - whose inter-judge disagreement we reframe not as noise but as a regulatory uncertainty signal warranting human arbitration. We validate this approach through a ground truth corpus of 49 annotated prompt/response pairs across five regulatory criteria, evaluated by four small language models (SLMs, 1.7B-7B parameters) running fully on-premise. Agreement rates range from 51.5% (mistral:7b) to 69.1% (phi4-mini), with no single model dominating across all criteria - empirically motivating the Profile-as-jury design. We further document three structural failure modes in small regulatory judges and a judge-specific position bias that degrades agreement by up to 25 percentage points across three question-order conditions (original, reversed, permuted). govllm is released as open-source software to support reproducible AI governance research.

Medical diagnosis is not a single prediction from a fully specified vignette. It is a sequential workup: clinicians decide what evidence to obtain, revise a differential diagnosis, and stop when the diagnosis is sufficiently supported. Most medical AI benchmarks instead reveal the relevant context upfront and score only the final answer, making unsupported correct guesses, premature closure, inefficient workups, and poor uncertainty updating invisible. We introduce DDX-TRACE, a physician-adjudicated benchmark for multimodal neuroradiology that evaluates diagnostic trajectories under hidden evidence over 211 challenging cases. Each case begins with limited clinical history; models request imaging studies in free form, receive matched image bundles when available, update a probabilistic differential diagnosis after each turn, and stop with a localized final diagnosis. Evaluating state-of-the-art VLMs, we find that final diagnosis scores can substantially misrepresent workup quality: models may guess plausible diagnoses without essential evidence, request useful studies but misinterpret raw images, or acquire evidence inefficiently while updating uncertainty poorly. Controlled evidence variants isolate bottlenecks in planning, visual evidence extraction, and downstream differential reasoning. DDX-TRACE shifts medical AI evaluation from final answers to evidence-supported diagnostic trajectories.

AI-assisted code review tools typically operate as generic "expert reviewer" agents, producing homogeneous findings regardless of the analysis type needed. We present a system that constrains AI reviewer behavior through philosophical dispositions -- coherent personality lenses grounded in specific epistemological traditions (Pyrrhonist Skepticism, Navya-Ny=aya logic, Diogenes' Cynicism, Confucian relational ethics) that direct attention to structurally different types of issues. Each disposition is defined apophatically (by what it refuses to do), equipped with a self-monitoring failure mode (hamartia), and orchestrated in sequence by role protocols. We evaluate this system on 50 merged pull requests across 7 repositories spanning 5 programming languages (Python, Go, C++, Java, Terraform), 5 organizations (2 enterprise, 3 open-source), and 2 temporal eras (pre-AI 2020, post-AI 2024--2026). The disposition system achieves 46% convergence with human reviewers (validating signal quality), identifies unique findings at a 75% rate, and produces no findings judged false-positive by the author across 601 total findings (inter-rater agreement was not assessed and remains a limitation). A controlled baseline comparison demonstrates that 51% of disposition findings are not produced by the same model using generic "expert reviewer" prompting, and these unique findings target structural, operational, and logical concerns rather than standard code-level issues. Preliminary cross-model validation (Claude Opus vs.\ GPT Codex 5.3-xhigh) on 3 PRs shows 100% framework-structure adherence with 39% finding-level agreement, suggesting the framework provides real behavioral constraint while preserving model-specific analytical perspective.

With the advancement of AI capabilities, AI reviewers are beginning to be deployed in scientific peer review, yet their capability and credibility remain in question: many scientists simply view them as probabilistic systems without the expertise to evaluate research, while other researchers are more optimistic about their readiness without concrete evidence. Understanding what AI reviewers do well, where they fall short, and what challenges remain is essential. However, existing evaluations of AI reviewers have focused on whether their verdicts match human verdicts (e.g., score alignment, acceptance prediction), which is insufficient to characterize their capabilities and limits. In this paper, we close this gap through a large-scale expert annotation study, in which 45 domain scientists in Physical, Biological, and Health Sciences spent 469 hours rating 2,960 individual criticisms (each targeting one specific aspect of a paper) from human-written and AI-generated reviews of 82 Nature-family papers on correctness, significance, and sufficiency of evidence. On a composite of all three dimensions, a reviewing agent powered by GPT-5.2 scores above each paper's top-rated human reviewer (60.0% vs. 48.2%, p = 0.009), while all three AI reviewers (including Gemini 3.0 Pro and Claude Opus 4.5) exceed the lowest-rated human across every dimension. AI reviewers' accurate criticisms are also more often rated significant and well-evidenced, and surface a distinct 26% of issues no human raises. However, AI reviewers overlap far more than humans do (21% vs. 3% for cross-reviewer pairs), and exhibit 16 recurring weaknesses humans do not share, such as limited subfield knowledge, lack of long context management over multiple files, and overly critical stance on minor issues. Overall, our results position current AI reviewers as complements to, not substitutes for, human reviewers.

Trust calibration -- aligning user trust judgment with model capability -- is crucial for safe deployment of explainable AI (XAI), yet is often evaluated via global trust ratings detached from objective performance evidence. We present a preregistered, incentivized between-subject online study (N=418 representative UK sample) on explainable skin-lesion classification that disentangles expectation-setting from experienced performance. Participants completed 15 case evaluations using a fixed XAI panel (malignancy score, reliability score, and saliency map). We systematically manipulated five experimental onboarding conditions varying example-based information and limitation disclosures with five stimulus packages naturally varying observed prediction quality. Calibration was operationalized as the deviation between trust-related judgments (TAIS and case-wise ratings) and objective performance benchmarks for the encountered cases, analysed with hierarchical mixed-effects models. Only limitation disclosure for case-wise measures reliably impacts trust calibration, and short-term experience did not yield progressive calibration. Further, the experienced package of stimuli explained substantially more variance than the experimental manipulation. However, participants were hard-pressed to differentiate between case-wise perceived trust, trustworthiness, and accuracy estimation. We discuss implications for designing limitation communication and for measuring and analysing calibration metrics in XAI evaluations. All study materials and data of this study are publicly available for replication and further academic use.

The rapid progress of generative artificial intelligence has exposed fundamental limitations in existing evaluation methodologies, particularly for open-ended, creative, and human-facing tasks. Traditional automatic metrics rely on surface-level statistical similarity and often fail to reflect human perceptions of quality, while purely human evaluation, although reliable, is costly, subjective, and difficult to scale. Recent approaches using large language models as evaluators offer improved scalability but frequently lack explicit grounding in human-defined evaluation principles, leading to bias and inconsistency. In this paper, we introduce Quantifying Qualitative Judgment (QQJ), a scalable and human-centric evaluation framework that explicitly bridges the gap between human judgment and automated assessment. QQJ separates the definition of quality from its execution by anchoring evaluation in expert-designed, multi-dimensional rubrics and calibrating large language model evaluators to align with expert reasoning using a small, high-quality annotation set. This design enables consistent, interpretable, and scalable evaluation across diverse generative tasks and modalities. Extensive experiments on text and image generation demonstrate that QQJ achieves substantially stronger alignment with human judgment than traditional automatic metrics and unconstrained LLM-based evaluators. Moreover, QQJ exhibits improved stability across repeated evaluations and superior diagnostic capability in identifying critical failure modes such as hallucination and intent mismatch. These results indicate that structured qualitative judgment can be operationalized at scale without sacrificing interpretability or human alignment, positioning QQJ as a practical foundation for reliable evaluation of modern generative AI systems.

Tremendous efforts have been put into evaluating the inclusivity and effectiveness of AI systems across cultures. However, the cultural capabilities considered in much of the literature remain vaguely defined, are referred to using interchangeable terminology, and are typically limited to recalling accurate information about various demographics, regions, and nationalities. To address this construct ambiguity, we draw from Intercultural Communication scholarship and propose a three-level taxonomy of AI-relevant cultural capabilities: Cultural Awareness answers "Does the model know?", Cultural Sensitivity answers "How does it frame its knowledge?", and Cultural Competence answers "Can it adapt as the interaction evolves?". Beyond conceptual clarification, we position this taxonomy as a practical tool for improving the validity and interpretability of AI evaluation in real-world, multicultural settings. Without such construct clarity, evaluation results risk overstating model capabilities and may lead to inappropriate deployment decisions in culturally sensitive contexts.

The use of large language models to assess user states in conversational and adaptive systems is based on the assumption that the metrics used for such assessment are stable and interpretable at the level of individual scores. This paper empirically tests this assumption, focusing on the psychometric reliability of artificial intelligence (AI) measures of user states. This study employed replication evaluation procedures to assess the repeatability of a broad set of metrics across three different bimodal large language models (GPT-4o audio, Gemini 2.0 Flash, Gemini 2.5 Flash). Analyses include both individual score reliability and aggregated reliability, allowing us to distinguish metrics potentially useful for real-time adaptation from those that retain their value only in aggregated analyses. The results demonstrate that metric reliability cannot be considered a default property in interpretive domains. The lack of stability at the level of individual scores precludes the interpretation of such scores as indicators of user state in real-time adaptive systems, even if these metrics demonstrate stability after aggregation. At the same time, the study indicates that individually unstable metrics can retain analytical utility in post-hoc studies, identifying rules governing interactions and their relationships with user experience parameters such as satisfaction, trust, and engagement. The main contribution of this work, besides quantifying the severity of the problem (only 31 of 213 metrics met the criteria), is the proposal of a replicable evaluation framework, enabling measurable evaluations of metric applicability. This approach supports more responsible AI design of adaptive systems, in which the interpretation of results requires explicit validation of reliability and monitoring for violations over time.

Accurately predicting individual aesthetic evaluation for images is a fundamental challenge for AI. Various deep learning (DL)-based models have been proposed for this task, training on image evaluation data to extract objective low-level features. However, aesthetic preferences are inherently subjective and individual-dependent. Accurate prediction thus requires the extraction of high-level semantic features of images and the active collection of preference information from the target individual. To address this issue, we focus on the utility of Large Language Models (LLMs) pretrained on vast amounts of textual data, and develop an integrated DL-LLM system. The system actively elicits aesthetic preferences through LLM-based semi-structured interviews and predicts aesthetic evaluation by leveraging both low-level and high-level features. In our experiments, we compare the proposed system against conventional systems, human predictors, and the target individual's own re-evaluations after a certain time interval. Our results show that the proposed system outperforms all of them, with particularly strong performance on highly-rated images. Moreover, the prediction error of the proposed system is smaller than within-person variability, while human predictors show the largest error, likely due to the influence of their own aesthetic values. These results suggest that AI may be better positioned than others or one's future self to capture individual aesthetic preferences at a given point. This opens a new question of whether AI could serve as a deeper interpreter of human aesthetic sensibility than humans themselves.

AI-enabled features built on LLMs and agentic workflows are difficult to test, debug, and reproduce, especially for product-focused software engineers without a machine learning background. We present the AI Toolkit plugin for JetBrains IDEs, which brings tracing and evaluation directly into the Run/Debug loop. A mixed methods study with practitioners presents three consistent needs: (1) make evaluation regular and repeatable, (2) expose traces at the moment of execution, and (3) minimize setup and context switching. Guided by these needs, the AI Toolkit introduces an IDE-native workflow: run-triggered trace capture; immediate, hierarchical inspection; one-click "Add to Dataset" from traces; and unit-test-like evaluations with pluggable metrics. The first release in PyCharm shows promising early signals - strong conversion when promoted at Run, sustained usage among those who capture traces, and low churn - suggesting that IDE-native observability lowers activation energy and helps developers adopt disciplined practices. We detail the design and implementation of the AI Agents Debugger and AI Evaluation, report initial adoption telemetry, and outline next steps to broaden framework coverage and scale evaluations. Together, these results indicate that integrating AI observability and evaluation into everyday IDE workflows can make modern AI development accessible to non-ML specialists while preserving software-engineering practices.

Recent advancements in generative AI facilitate large-scale synthetic data generation for model evaluation. However, without targeted approaches, these datasets often lack the sociotechnical nuance required for sensitive domains. We introduce NodeSynth, an evidence-grounded methodology that generates socially relevant synthetic queries by leveraging a fine-tuned taxonomy generator (TaG) anchored in real-world evidence. Evaluated against four mainstream LLMs (e.g., Claude 4.5 Haiku), NodeSynth elicited failure rates up to five times higher than human-authored benchmarks. Ablation studies confirm that our granular taxonomic expansion significantly drives these failure rates, while independent validation reveals critical deficiencies in prominent guard models (e.g., Llama-Guard-3). We open-source our end-to-end research prototype and datasets to enable scalable, high-stakes model evaluation and targeted safety interventions (https://github.com/google-research/nodesynth).

Chatbot usage has increased, including in fields for which they were never developed for--notably mental health support. To that end, we introduce Validations of Ethical and Responsible AI in Mental Health (VERA-MH), a novel clinically-validated evaluation for safety of chatbots in the context of mental health support. The first iteration of VERA-MH focuses on Suicidal Ideation (SI) risks, by assessing how well chatbots can responds to users that might be in crisis. VERA-MH is comprised of three steps: conversation simulation, conversation judging and model rating. First, to simulate conversations with the chatbot under evaluation, another chatbot is tasked with role-playing users based on specific personas. Such user personas have been developed under clinical guidance, to make sure that, among others, multiple risk factors, demographic characteristics and disclosure factors were represented. In the judging step, a second support model is used as an LLM-as-a-Judge, together with a clinically-developed rubric. The rubric is structured as a flow, with a single Yes/No question asked each time, to improve answers' consistency and highlight models' failure modes. In the last stage, results of each conversation are aggregated to present the final evaluation of the chatbot. Together with the framework, we present the result of the evaluations for four leading LLM providers.

Text-to-image (T2I) generative models are increasingly used to produce content for education, media, and public-facing communication, and are starting to be integrated into higher-impact pipelines. Since generated images tend to reinforce stereotypes, producing representational erasure via "default" depictions and shaping perceptions of who belongs in certain roles, a growing body of work has proposed metrics to quantify gender bias in T2I outputs. Yet existing evaluations remain fragmented. Metrics are often reported without a shared view of what they measure, what assumptions they entail, or how their results should be interpreted under different deployment contexts. This limits the usefulness of gender bias measurement for both technical auditing and emerging governance discussions. We propose a risk-aligned auditing framework for gender bias in T2I models composed of three constituents that connects risk categories, evaluation metrics, and harms. First, we identify risk-tiered use-case profiles aligned with the EU AI Act's risk categories to motivate why auditing expectations may vary with deployment contexts and stakeholder exposure. Second, we construct a metric catalog that consolidates gender-bias evaluation methods and organizes them in three measurement categories: gender prediction, embedding similarity, and downstream task. Third, we introduce a harm typology that maps context-dependent harm categories (e.g., representational, quality-of-service) to specific risk-tired scenarios. Finally, we introduce THUMB cards (Text-to-image Harms-informed Use-case-aligned Metrics of gender Bias) that help formulate auditing systematically by the incorporation of context, scenario and bias manifestation, harm hypotheses, and audit strategy.

Recent published evidence from frontier laboratories shows that contemporary AI models can recognise evaluation contexts, latently represent them, and behave differently under those contexts than under deployment-continuous conditions. Anthropic's BrowseComp incident, the Natural Language Autoencoder findings on SWE-bench Verified and destructive-coding evaluations, and the OpenAI / Apollo anti-scheming work all document instances of this phenomenon. We argue that these findings create a claim-validity problem for safety conclusions drawn from frontier evaluations. We introduce the Evaluation Differential (ED), a conditional divergence in a target behavioural property between recognised-evaluation and deployment-continuous contexts, define a normalised effect-size form (nED) for cross-property comparison, and prove that marginal evaluation scores cannot identify ED. We develop a typology of safety claims (ED-stable, ED-degraded, ED-inverted, ED-undetermined) by their warrant-status under documented divergence, and specify TRACE (Test-Recognition Audit for Claim Evaluation), an audit protocol that wraps existing evaluation infrastructure and produces restricted claims rather than capability scores. We apply the framework retrospectively to three publicly documented evaluation incidents and discuss governance implications for system cards, conformity assessment, and the international network of AI safety and security institutes. TRACE does not eliminate adversarial adaptation; it disciplines the claims drawn from evaluation evidence by making explicit the conditions under which that evidence was produced.

Deploying machine learning in regulated financial environments -- credit risk, fraud detection, and anti-money laundering -- exposes critical vulnerabilities in algorithmic reproducibility. While early financial ML addressed statistical challenges such as backtest overfitting, deep neural networks and Generative AI have introduced mechanical nondeterminism rooted in hardware and architecture. This survey provides a systems perspective on reproducibility failures across three modalities now dominant in financial AI: tabular models (post-hoc explanation variance), graph networks (stochastic sampling and temporal asynchrony), and LLM-based agentic workflows (batch-dependent divergence and trajectory drift). We supplement the literature analysis with first-party experiments on public financial datasets -- quantifying explanation rank instability in credit scoring, prediction flip rates in GNN-based fraud detection, and tensor-parallel-induced output divergence in LLM entity extraction. We propose a layered evaluation framework linking modality-specific metrics (RBO, D_cos, TDI, PSD) to audit readiness, and empirically validate the complementarity of logit-level and semantic-level determinism measures.

AI deployment in sensitive domains such as health care, credit, employment, and criminal justice is often treated as unsafe to authorize until model internals can be explained. This often leads to an excessive reliance on mechanistic interpretability to address a deployment challenge beyond its intended scope. We argue that the gate should instead be calibrated verification: authorization should be domain-scoped, independently checkable, monitored after release, accountable, contestable, and revocable. The reason is twofold. First, model capability is uneven across nearby tasks, so authorization must attach to a specific use rather than to a model in general. Second, societies have long governed opaque expertise through credentials, monitoring, liability, appeal, and revocation rather than mechanism-level explanation. Recent evidence reinforces this distinction between mechanistic understanding and deployment authority: a 53-percentage-point gap between internal representations and output correction shows that understanding may not translate into action, while one scoping review found that only 9.0% of FDA-approved AI/ML device documents contained a prospective post-market surveillance study. We propose Verification Coverage, a six-component reportable standard with a minimum-composition rule, as the metric that should sit beside capability scores in model cards, leaderboards, and regulatory disclosures.

The safety of mental health AI is often judged at the wrong temporal scale. Current evaluations typically score isolated responses, endpoint outcomes, or aggregate dialogue quality, while clinically consequential failures may arise from the order and accumulation of interactions themselves, including delayed escalation, repeated reinforcement, dependency formation, failed repair, and gradual deterioration across turns. This paper argues that this mismatch is not merely a limitation of evaluation coverage but a source of invalid safety conclusions. We introduce Temporal Safety Non-Identifiability, a formal account of why safety properties that depend on sequence, timing, accumulation, or recovery cannot be certified by protocols that discard those features. From this formalization, we develop SCOPE (Safety Claims Over Preserved Evidence) as a general principle for aligning safety claims with the evidence an evaluation actually retains, and instantiate it as SCOPE-MH, a mental-health instantiation of this reporting standard. We operationalize SCOPE-MH through a proof-of-concept on the AnnoMI dataset of expert-annotated motivational interviewing conversations, which reveals mechanisms of failure that per-turn behavior scoring does not represent. We propose SCOPE-MH as a diagnostic complement to existing evaluation infrastructure and argue that evaluation preserving temporal evidence is necessary, not optional, for safety-critical mental health AI deployment.

AI measurement science has a wide variety of methodologies and measurements for comparing AI systems, resulting in what often appear to be "apples-to-oranges" comparisons across AI evaluations. To move toward "apples-to-apples" comparisons in real-world AI evaluations, this work advocates for methodological transparency in evaluation scenarios, operational grounding, and human-centered design (HCD) principles. We propose a repeatable process for transforming high-level use cases to detailed scenarios by eliciting use cases from subject matter experts (SMEs) via a structured AI Use Case Worksheet with six key elements: use case, sector, user (direct and indirect), intended outcomes, expected impacts (positive and negative), and KPIs and metrics. We demonstrate utility of the worksheet and process in the U.S. financial services sector. This paper reports on example high-level AI use cases identified by financial services sector SMEs: cyber defense enablement, developer productivity, financial crime aggregation, suspicious activity report (SAR) filing, credit memo generation, and internal call center support. These AI use cases provided are illustrative of the process and not exhaustive. Central to our work is a three-stage expansion pipeline combining LLM prompting with human reviews to generate 107 scenarios from those use cases elicited from SMEs. This process integrates iterative human reviews at every juncture to ensure operational grounding: for scenario titles and descriptions; for core scenario elements like users, benefits and risks, and metrics; and for scenario narratives and evaluation objectives. Human checkpoints ensure scenarios remain reflective of real-world usage and human needs. We describe a validation rubric to assess scenario quality. By defining key scenario components, this work supports a more consistent and meaningful paradigm for human-centered AI evaluations.

Despite the rapid development of AI reviewers, evaluating such systems remains challenging: metrics favor overlap with human reviews over correctness. However, since human reviews often cover only a subset of salient issues and sometimes contain mistakes, they are unreliable as gold references. To address this, we build category-specific benchmark subsets and skip evaluation when the corresponding human reviews are missing to strengthen Completeness. We also leverage reviewer--author--meta-review discussions as expert annotations and filter unreliable reviews accordingly to strengthen Correctness. Finally, we introduce CoCoReviewBench, which curates 3,900 papers from ICLR and NeurIPS to enable reliable and fine-grained evaluation of AI reviewers. Analysis shows that AI reviewers remain limited in correctness and are prone to hallucinations, and highlights reasoning models as more effective reviewers, motivating further directions for improving AI reviewers. Benchmarks and models are available at https://github.com/hexuandeng/CoCoReviewBench.

Generative AI systems achieve impressive performance on standard benchmarks yet fail to deliver real-world utility, a disconnect we identify across 28 deployment cases spanning education, healthcare, software engineering, and law. We argue that this benchmark utility gap arises from three recurring failures in evaluation practice: proxy displacement, temporal collapse, and distributional concealment. Motivated by these observations, we argue that generative AI evaluation requires a paradigm shift from static benchmark-centered transparency toward stakeholder, goal, and context-conditioned utility transparency grounded in human outcome trajectories. Existing evaluations primarily characterize properties of model outputs, while deployment success depends on whether interaction with AI improves stakeholders' ability to achieve their goals over time. The missing construct is therefore utility: the change in a stakeholder's capability induced through sustained interaction with an AI system within a deployment context. To operationalize this perspective, we propose SCU-GenEval, a four-stage evaluation framework consisting of stakeholder-goal mapping, construct-indicator specification, mechanism modeling, and longitudinal utility measurement. To make these stages practically deployable, we introduce three supporting instruments: structured deployment protocols, context-conditioned user simulators, and persona- and goal-conditioned proxy metrics. We conclude with domain-specific calls to action, arguing that progress in generative AI must be evaluated through measurable improvements in human outcomes rather than benchmark performance alone.

Creative AI systems are typically evaluated at the level of individual utility, yet creative outputs are consumed in populations: an idea loses value when many others produce similar ones. This creates an evaluation blind spot, as AI can improve individual outputs while increasing population-level crowding. We introduce a human-relative framework for benchmarking AI-induced human diversity collapse without requiring human-AI interaction data, providing an ex ante protocol to estimate crowding risk from model-only generations and matched unaided human baselines. By modeling ideas as congestible resources, we show that source-level crowding is identifiable from within-distribution comparisons, yielding an excess-crowding coefficient $Δ$ and a human-relative diversity ratio $ρ$. We show that $ρ\ge1$ is the no-excess-crowding parity condition and connect $Δ$ to an adoption game with exposure-dependent redundancy costs. Across short stories, marketing slogans, and alternative-uses tasks, three frontier LLMs fall below parity across crowding kernels. Estimates stabilize with feasible model-only sample sizes. Importantly, generation-protocol variants show that crowding can be reduced through targeted design, making diversity collapse an actionable, development-time evaluation target for population-aware creative AI.

Current Artificial Intelligence (AI)-based tutoring systems (AI tutors) are primarily evaluated based on the pedagogical quality of their feedback messages. While important, pedagogy alone is insufficient because it ignores a critical question: what do students actually do with the feedback they receive? We argue that AI tutor evaluation should be extended with a behavioral dimension grounded in student interaction data, which complements pedagogical assessment. We propose an evaluation framework and apply it to 10,235 code submissions with corresponding AI tutor feedback from an introductory undergraduate programming course to measure whether students act on tutor feedback and whether those actions are applied correctly. Using this framework to compare two deployed AI tutors across different semesters in a large-scale introductory computer science course reveals substantial differences in student engagement patterns that are not captured by pedagogy-only evaluation. Moreover, these engagement-based behavioral signals are more strongly associated with student perception of helpful feedback than pedagogical quality alone, providing a more complete and actionable picture of AI tutor performance.

This intervention study investigates the use of counterarguments in writing for critical thinking by students in the context of Generative AI (GenAI). This is especially as risks of cheating and cognitive offloading exist with the use of GenAI. We presented 36 students in a particular university course with 4 carefully selected thesis statements (from a set of popular debates) to write about anyone of them. We used six established rubrics (focus, logic, content, style, correctness and reference) to conduct three human assessments (two student peer-reviews and one experienced teacher) per writeup on a 5-point Likert scale for all the qualified samples (n) of 35 submissions (after disqualifying one for irregularity). Using the same rubrics and guidelines, we also assessed the submissions using six frontier LLMs as judges. Our mixed-method design included qualitative open-ended feedback per assessment and quantitative methods. The results reveal that (1) the students' self-written counterarguments to AI-generated content contains logic, among other things, which is a key component of critical thinking, and (2) GenAI can be successfully used at scale to assess students' written work, based on clear rubrics, and these assessments generally align with human assessments as shown with Gwets AC2 inter-rater reliability values of 0.33 for all the models except one.

The evaluation of explainable AI (XAI) methods is affected by a lack of standardization. Metrics are inconsistently defined, incompletely reported, and rarely validated against common baselines. In this paper, we identify transparency of evaluation reporting as a central, under-addressed problem. We propose the XAI Evaluation Card, a documentation template analogous to model cards, designed to accompany any study that introduces an XAI evaluation metric. The card covers explicit declaration of target properties, grounding levels, metric assumptions, validation evidence, gaming risks, and known failure cases. We argue that adopting this template as a community norm would reduce evaluation fragmentation, support meta-analysis, and improve accountability in XAI research.

Readers of applied-domain LLM capability evaluations want to know what AI systems can currently do. That literature answers a related, but consequentially different, question: what older, cheaper, less-elicited models could do months or years earlier (a 2026 paper evaluating GPT-3.5 or GPT-4 zero-shot, say, against a frontier of reasoning-capable, tool-using systems like GPT-5.5 Pro and Claude Opus 4.7), often reported with sparse configuration details and abstracted upward into claims about "AI" that propagate through citations, media, and policy. We measure the 'publication elicitation gap' (the gap between these answers) in a pre-registered audit of 112,303 LLM-keyword-matched candidate records (2022-01 to 2026-04; 18,574 admissible, 4,766 full-paper texts retrievable), comparing tested models to the contemporaneous frontier on the Epoch AI Capabilities Index (ECI), reproduced under Arena Elo and Artificial Analysis. The median paper evaluates a model +10.85 ECI (~1.4x the distance between Claude Sonnet 3.7 and Claude Opus 4.5) behind the contemporaneous frontier at evaluation time (H1); an exploratory rational-lag baseline (H8) decomposes this into ~25% peer-review latency, ~75% excess lag. The gap is widening at +5.53 ECI/year (H2; 95% CI [+5.03, +5.83]). Meanwhile, only 3.2% of abstracts (21.2% of full-texts) disclose reasoning-mode status on reasoning-capable models (H4) and 52.5% (95% CI [48.2, 56.9]) state conclusions at the level of "AI" rather than the evaluated model(s), rising at OR = 1.23/year. Proposed remedies include API-access subsidies and editorial enforcement of reporting frameworks mandating configuration-surface disclosure (model snapshot, reasoning mode/effort, tool access, scaffolding, prompting, etc.); VERSIO-AI is a 13-item checklist (Core 3 desk-reject) extending existing frameworks at the elicitation surface, with per-DOI analysis at frontierlag.org.

Frontier AI safety claims - published assertions that a highly capable general-purpose model is below a threshold of concern, adequately mitigated, or suitable for release - increasingly shape model deployment, governance, and public trust. Yet the artefacts needed to evaluate them are routinely withheld, producing an evidential inversion: the most consequential claims in AI safety are often the least reproducible. This position paper argues that NeurIPS should require reproducibility standards for papers making such claims, treating non-reproducibility not as a transparency preference but as an evaluation-methodology failure. The 2026 International AI Safety Report [Bengio et al., 2026] concludes that reliable pre-deployment safety testing has become harder to conduct and that models now distinguish test from deployment contexts; the 2025 Foundation Model Transparency Index [Wan et al., 2025] reports a sector-average transparency score of 40/100 with no major developer adequately disclosing train-test overlap; contemporaneous measurement-theory work shows that attack-success-rate comparisons across systems are often founded on low-validity measurements [Chouldechova et al., 2025]. We propose a three-tier disclosure framework, distinguishing public, controlled, and claim-restricted disclosure, paired with a mandatory claim inventory, scope statements, and a phased implementation path with graduated sanctions. The framework treats secrecy and openness as endpoints of a spectrum, with controlled review (via a federated colloquium of qualified secure-review hosts) covering claims whose artefacts cannot be released publicly, and right-scaling claims whose artefacts cannot be reviewed even confidentially. The standard the community applies to its most consequential claims should be at least as high as the standard it applies to its least.

Human evaluation remains the primary standard for assessing modern AI systems, yet annotator disagreement, bias, and variability make system rankings fragile under standard majority vote aggregation. Majority vote discards annotator reliability and item-level ambiguity, often yielding unstable comparisons across annotator subsets. We introduce STABLEVAL, a disagreement-aware evaluation framework that models latent item correctness and annotator-specific confusion patterns to produce posterior expected item credit and calibrated agent-level scores. Unlike label-denoising approaches such as Dawid-Skene, STABLEVAL is explicitly designed for stable and uncertainty-aware system evaluation rather than hard label recovery. We formalize ranking stability as a first-class evaluation objective and analyze how aggregation methods preserve or distort underlying annotator behavior. Across controlled synthetic experiments and multiple real-world human-annotated benchmarks, majority vote exhibits increasing score error and ranking instability under annotator heterogeneity and adversarial noise, while STABLEVAL yields more stable and statistically grounded system rankings. These results demonstrate that modeling disagreement is essential for robust and reproducible AI evaluation.

This work establishes a foundational framework for standardizing AI evaluation RCTs (sometimes called human uplift studies). Drawing on established experimental practices from disciplines with established RCT traditions, including software engineering, economics, clinical and health sciences, and psychology, we adopt the (Shadish et al., 2002) four-validity framework and extend it with a fifth principle on transparency, repeatability, and verification adapted from the Transparency and Openness Promotion (TOP) Guidelines (Center for Open Science, 2025). We operationalize all five principles into 33 guidelines adapted for AI evaluation RCT contexts, expressed as requirements with rationales, implementation instructions, and evidence bases. We position the principles and guidelines as serving three key roles for AI evaluation RCTs: a design tool for planning studies, an evaluation rubric for assessing existing work, and a blueprint for standard setting as the field converges on norms. Our framework extends prior work by centering evaluation on human performance rather than model output alone, formalizing causal inference through RCT methodology for AI contexts, integrating heterogeneity analysis and practical significance assessment, implementing a graded transparency and repeatability framework, and addressing AI-specific challenges including model versioning, human-AI interaction dynamics, contamination and spillover effects, and equitable impact assessment.

Trust in clinical artificial intelligence (AI) cannot be reduced to model accuracy, fluency of generation, or overall positive user impression. In medicine, trust must be engineered as a measurable system property grounded in evidence, supervision, and operational boundaries of AI autonomy. This article proposes a practical framework for trustworthy clinical AI built around three principles: evidence, supervision, and staged autonomy. Rather than replacing deterministic clinical logic wholesale with end-to-end black-box models, the proposed approach combines a deterministic core, a patient-specific AI assistant for contextual validation, a multi-tier model escalation mechanism, and a human supervision layer for verification, escalation, and risk control. We demonstrate that trust also depends on selective verification of clinically critical findings, bounded clinical context, disciplined prompt architecture, and careful evaluation on realistic cases. Classifier-driven modular prompting is examined as an incremental path to scaling clinical depth without sacrificing prompt performance and without waiting for complete rule-based coverage. To operationalize trust, a set of trust metrics is proposed, built on metrological principles -- measurement uncertainty, calibration, traceability -- enabling quantitative rather than subjective assessment of each architectural layer. In this perspective, trustworthy clinical AI emerges not as a property of an individual model, but as an architectural outcome of a system into which evidence trails, human oversight, tiered escalation, and graduated action rights are embedded from the outset.

AI-for-Science (AI4Science) is increasingly transforming scientific discovery by embedding machine learning models into prediction, simulation, and hypothesis generation workflows across domains. However, the effectiveness of these models is fundamentally constrained by the AI-readiness of scientific data, for which no scalable and systematic evaluation mechanism currently exists. In this work, we propose SciHorizon-DataEVA, a novel agentic system to scalable AI-readiness evaluation of heterogeneous scientific data. At the evaluation-criteria level, we introduce the Sci-TQA2 principles, which organize AI-readiness into four complementary dimensions: Governance Trustworthiness, Data Quality, AI Compatibility, and Scientific Adaptability. Each dimension is decomposed into measurable atomic elements that enable fine-grained and executable assessment. To operationalize these principles at scale, we develop Sci-TQA2-Eval, a hierarchical multi-agent evaluation approach orchestrated through a directed, cyclic workflow. Our Sci-TQA2-Eval dynamically constructs dataset-aware evaluation specifications by combining lightweight dataset profiling, applicability-aware metric activation, and knowledge-augmented planning grounded in domain constraints and dataset-paper signals. These specifications are executed through an adaptive, tool-centric evaluation mechanism with built-in verification and self-correction, enabling scalable and reliable assessment across heterogeneous scientific data. Extensive experiments on scientific datasets spanning multiple domains demonstrate the effectiveness and generality of SciHorizon-DataEVA for principled AI-readiness evaluation.

Among the many challenges hindering the responsible development and deployment of AI, arguably none has faced more intense scrutiny than bias in its various forms. This underscores the widespread concerns across AI researchers that model outputs, e.g., from generative AI, may encode structural distributional imbalances (stemming from training data or model design) that may amplify social inequality or introduce systemic distortions across application domains ranging from biodiversity to disaster mitigation. Yet, relatively little work has investigated the geographical nature of bias or developed measurable benchmarks for what it means for (generative) AI to be unbiased. In this chapter, we investigate this issue through a literature review. As foundation models are reshaping the landscape of bias research, we examine work spanning both the pre-generative AI and generative AI periods. First, we identify a range of geographic biases. These biases span from representation bias in the training data and regional disparities in the factual recall of language models to the tendency of generative AI to over-proportionally favor prototypical places (called defaults). Then, we showcase how recent studies address the latter bias by evaluating geographic diversity in the outputs of generative AI across various cognitive levels, parameter settings, and output modalities.

Objective. Clinical AI documentation systems require evaluation methodologies that are clinically valid, economically viable, and sensitive to iterative changes. Methods requiring expert review per scoring instance are too slow and expensive for safe, iterative deployment. We present a case-specific, clinician-authored rubric methodology for clinical AI evaluation and examine whether LLM-generated rubrics can approximate clinician agreement. Materials and Methods. Twenty clinicians authored 1,646 rubrics for 823 clinical cases (736 real-world, 87 synthetic) across primary care, psychiatry, oncology, and behavioral health. Each rubric was validated by confirming that an LLM-based scoring agent consistently scored clinician-preferred outputs higher than rejected ones. Seven versions of an EHR-embedded AI agent for clinicians were evaluated across all cases. Results. Clinician-authored rubrics discriminated effectively between high- and low-quality outputs (median score gap: 82.9%) with high scoring stability (median range: 0.00%). Median scores improved from 84% to 95%. In later experiments, clinician-LLM ranking agreement (tau: 0.42-0.46) matched or exceeded clinician-clinician agreement (tau: 0.38-0.43), attributable to both ceiling compression and LLM rubric improvement. Discussion. This convergence supports incorporating LLM rubrics alongside clinician-authored ones. At roughly 1,000 times lower cost, LLM rubrics enable substantially greater evaluation coverage, while continued clinical authorship grounds evaluation in expert judgment. Ceiling compression poses a methodological challenge for future inter-rater agreement studies. Conclusion. Case-specific rubrics offer a path for clinical AI evaluation that preserves expert judgment while enabling automation at three orders lower cost. Clinician-authored rubrics establish the baseline against which LLM rubrics are validated.

While mechanistic interpretability (MI) has produced important insights into neural network internals, the field has yet to establish a standardized system to audit experiments. As such, many of its findings remain underutilized in safety-critical applications such as medical AI and autonomous systems, as stakeholders cannot certify their validity. Recent work demonstrates this concretely: two papers found conflicting conclusions for the same behavior, and a third study revealed that both were partially correct but incomparable due to methodological inconsistencies. Without standardized auditing, such ambiguities hinder adoption in high-stakes contexts requiring strong correctness guarantees. We call for the MI community to work towards developing a novel reviewing system that complements peer review via: (1) Continuous reviewing supported by a \emph{Collaborative Reviewing Platform} where meta-science results and discussions (such as critiques, negative results, post-hoc extensions, reproductions, replications, and partial results) that fit outside of papers are organized and discussed, allowing for comments and revisions to be made at any time (2) Generalizing good practices found on this platform into expert-verified guidelines and protocols to improve auditing efficiency, and (3) Source-based auditing systems that track arguments which claims depend on. This position paper encourages constructive debate over the necessity, design and implementation of such a framework, providing early concrete examples to help catalyze these dialogues. Overall, we propose that auditing MI itself is essential for its application in AI safety, industry, and governance.

Artificial intelligence now decides who receives a loan, who is flagged for criminal investigation, and whether an autonomous vehicle brakes in time. Governments have responded: the EU AI Act, the NIST Risk Management Framework, and the Council of Europe Convention all demand that high-risk systems demonstrate safety before deployment. Yet beneath this regulatory consensus lies a critical vacuum: none specifies what ``acceptable risk'' means in quantitative terms, and none provides a technical method for verifying that a deployed system actually meets such a threshold. The regulatory architecture is in place; the verification instrument is not. This gap is not theoretical. As the EU AI Act moves into full enforcement, developers face mandatory conformity assessments without established methodologies for producing quantitative safety evidence - and the systems most in need of oversight are opaque statistical inference engines that resist white-box scrutiny. This paper provides the missing instrument. Drawing on the aviation certification paradigm, we propose a two-stage framework that transforms AI risk regulation into engineering practice. In Stage One, a competent authority formally fixes an acceptable failure probability $δ$ and an operational input domain $\varepsilon$ - a normative act with direct civil liability implications. In Stage Two, the RoMA and gRoMA statistical verification tools compute a definitive, auditable upper bound on the system's true failure rate, requiring no access to model internals and scaling to arbitrary architectures. We demonstrate how this certificate satisfies existing regulatory obligations, shifts accountability upstream to developers, and integrates with the legal frameworks that exist today.

As artificial intelligence (AI) systems are increasingly deployed across critical domains, their security vulnerabilities pose growing risks of high-profile exploits and consequential system failures. Yet systematic approaches to evaluating AI security remain underdeveloped. In this paper, we introduce AVISE (AI Vulnerability Identification and Security Evaluation), a modular open-source framework for identifying vulnerabilities in and evaluating the security of AI systems and models. As a demonstration of the framework, we extend the theory-of-mind-based multi-turn Red Queen attack into an Adversarial Language Model (ALM) augmented attack and develop an automated Security Evaluation Test (SET) for discovering jailbreak vulnerabilities in language models. The SET comprises 25 test cases and an Evaluation Language Model (ELM) that determines whether each test case was able to jailbreak the target model, achieving 92% accuracy, an F1-score of 0.91, and a Matthews correlation coefficient of 0.83. We evaluate nine recently released language models of diverse sizes with the SET and find that all are vulnerable to the augmented Red Queen attack to varying degrees. AVISE provides researchers and industry practitioners with an extensible foundation for developing and deploying automated SETs, offering a concrete step toward more rigorous and reproducible AI security evaluation.

In measurement theory, instruments do not simply record reality; they help constitute what is observed. The same holds for generative AI evaluation: benchmarks do not just measure, they shape what models appear to be. Functionalist benchmarks treat models as isolated predictors, while prescriptive approaches assess what systems ought to be. Both obscure the sociotechnical processes through which meaning and values are enacted, risking the reification of narrow cultural perspectives in pluralist contexts. This thesis advances a descriptive alternative. It argues that generative AI must be evaluated as a pluralist sociotechnical system and develops Machine-Society-Human (MaSH) Loops, a framework for tracing how models, users, and institutions recursively co-construct meaning and values. Evaluation shifts from judging outputs to examining how values are enacted in interaction. Three contributions follow. Conceptually, MaSH Loops reframes evaluation as recursive, enactive process. Methodologically, the World Values Benchmark introduces a distributional approach grounded in World Values Survey data, structured prompt sets, and anchor-aware scoring. Empirically, the thesis demonstrates these through two cases: value drift in early GPT-3 and sociotechnical evaluation in real estate. A final chapter draws on participatory realism to argue that prompting and evaluation are constitutive interventions, not neutral observations. The thesis argues that static benchmarks are insufficient for generative AI. Responsible evaluation requires pluralist, process-oriented frameworks that make visible whose values are enacted. Evaluation is therefore a site of governance, shaping how AI systems are understood, deployed, and trusted.

Evaluating AI-generated reviews by verdict agreement is widely recognized as insufficient, yet current alternatives rarely audit which concerns a system identifies, how it prioritizes them, or whether those priorities align with the review rationale that shaped the final assessment. We propose concern alignment, a diagnostic framework that evaluates AI reviews at the concern level rather than only at the verdict level. The framework's core data structure is the match graph, a bipartite alignment between official and AI-generated concerns annotated with match type, severity, and post-rebuttal treatment. From this artifact we derive an evaluation ladder that moves from binary accuracy to concern detection, verdict-stratified behavior, decision-aware calibration, and rebuttal-aware decomposition. In a pilot study of four public AI review systems evaluated in six configurations, concern-level analysis suggests that detection alone does not determine review quality; calibration is often the binding constraint. Systems detect non-trivial fractions of official concerns yet most mark 25--55% of concerns on accepted papers as decisive, where, under our operationalization, no official concern on accepted papers was treated as a decisive blocker. Identical overall verdict accuracy can conceal reject-heavy behavior versus low-recall profiles, and low full-review false decisive rates can partly reflect concern dilution rather than calibrated prioritization. Most systems do not emit a native accept/reject, and inferring it from review tone is method-sensitive, reinforcing the need for concern-level diagnostics that remain stable across inference choices. The contribution is a reusable evaluation framework for auditing which concerns AI reviewers identify, how they weight them, and whether those priorities align with the review rationale that informed the paper's final assessment.