Human Judgment

As generative AI is increasingly used as a source of personal financial guidance, understanding how people appraise such advice is important for supporting appropriate reliance. We conducted a randomized vignette experiment with 285 U.S. adults across eight financial decisions, independently varying three advice styles---AI, expert, and online community---and displayed source labels while holding the underlying recommendation consistent. Advice style most strongly shaped message and safety appraisals, Expert labels selectively increased perceived source knowledge, and decision context primarily shaped risk and safety appraisals. These appraisals were associated with downstream judgments, with models explaining 69.2% of overall quality, 75.9% of trust, and 82.9% of intended reliance. Expert-style advice also remained most preferred when shown without source labels. Our findings have implications for understanding financial advice evaluation, distinguishing the roles of advice style and source labels, and designing financial AI that supports grounded evaluation rather than simply maximizing trust.

Hiring is bilateral: employers assess fit, while candidates present and defend evidence of their qualifications. Yet résumé screening, the first gate, is commonly automated as a static, one-call judgment over a résumé-job pair. We study a two-agent alternative in which employer-side and candidate-side agents represent these roles, exchange evidence, and update their judgments before deciding who advances. We compare procedures on 600 constructed résumé-job pairs using GPT-5.5 and Claude Opus 4.7. Two-agent screening advances more applications (33.3% to 39.3% for GPT-5.5; 34.0% to 35.5% for Opus 4.7). Across three runs on the common 191-pair borderline pool, pass-instance rates rise from 4.5% to 26.2% and from 6.5% to 16.1%, respectively. This is not a uniform relaxation: two-agent screening rejects applications one-call advances, changing decisions in both directions. At similar pass volumes, the procedures advance different applications, and no one-call threshold recovers applications consistently selected by two-agent screening. Among discovery-selected cases re-executed in fresh runs, two-agent-only selections recur less often than shared selections, clearly under GPT-5.5 and less certainly under Opus 4.7, while a separate one-call follow-up shows no comparable decline. As hiring becomes agent-mediated on both sides, the screening procedure, not only the model behind it, shapes who reaches human review and how reliably that access recurs.

In collaborative tasks with asymmetric information, participants coordinate their understanding through interaction. We ask whether gaze provides evidence about grounding across two such tasks. Working from discrete behavioral annotations, we map HCRC MapTask (Anderson et al., 1991) and MUNDEX (Türk et al., 2023) into a shared partner/task/away vocabulary and compute gaze features around task-relevant dialogue units. In both corpora, aligned reference interpretations (MapTask) and UND (understood) judgments (MUNDEX) are associated with more task-directed gaze and with less partner-directed gaze, lower gaze entropy, and fewer gaze transitions. The associations are clearest for the participant leading the task: in giver-produced references, and in explainer judgments, which also co-vary with the explainee's gaze. In same-speaker MapTask reference chains, the speaker's gaze entropy is lower at the mention where a previously non-aligned referent becomes aligned. The best gaze feature groups improve modestly over controls under grouped cross-validation: temporal features in MapTask and raw proportions in MUNDEX. Because effects are small and several weaken when recurring participants rather than dialogues are the unit of inference, we treat gaze as one contributing cue to grounding, to be interpreted alongside task and dialogue context.

AI is changing what leaders must judge, explain, learn, and coordinate, yet existing measures do not capture these behaviors at the level needed to study leadership in AI-enabled work. We develop the AI Leadership Battery, which organizes 36 behaviorally specific subdimensions into 11 theory-specified content families. Following established scale-development procedures, the research used deductive item generation; content validation of definitional correspondence and definitional distinctiveness; exploratory factor analysis and item reduction; confirmatory factor analysis in independent samples; and tests of internal consistency reliability, convergent validity, discriminant validity, and criterion-related and incremental validity. Across the development and validation studies, the analyses provided evidence for the Battery's content, multidimensional structure, reliability, and distinction from selected orbiting constructs. The Battery also contributed additional information beyond orbiting constructs across organizational growth, decision speed, customer/stakeholder response capability, AI-enabled team performance, AI-enabled work experience, AI security and risk management, and AI adoption and integration. The resulting measure provides researchers with a behavioral framework for examining how leaders in AI-enabled work regulate judgment, learning, adaptation, transparency, and accountability.

Large language models (LLMs) are increasingly used in peer review at major AI conferences, yet novelty remains a persistent weak point. Existing benchmarks assess novelty as a single holistic score, making it difficult to diagnose which dimension a model misjudges or whether its evidence is faithful. We present NovGauge, a human-anchored benchmark for fine-grained novelty assessment diagnosis. The benchmark contains 619 paper pairs and 50 multi-paper sets, drawn from two expert sources: ICLR reviewer overlap claims and survey co-citations. Instances are independently labeled along three dimensions: task, problem, and method, capturing application goals, technical challenges, and solution approaches. We propose a cascading diagnostic pipeline that verifies per-dimension correctness, evidence grounding, and logical support. Evaluation of 18 LLMs shows hallucination rates ranging from 0% to 39% across dimensions, and among non-hallucinated correct-positive judgments, over 70% cite evidence fails to logically support the stated reason. The best-performing model, GPT-5.5, achieves 43-72% Verified F1 across dimensions, while most models retain less than half of their raw F1 after faithfulness verification. These results suggest that current LLMs remain far from reliable scientific novelty assessment, particularly when correctness is conditioned on faithful evidence grounding.

LLMs have been used to simulate human decision-making in professional settings, yet their behaviors in common-law jury trials remain unexplored. We study when and how a defendant's courtroom statement affects LLM-simulated jurors, focusing on persuasion, ideological bias, and background-based affinity. To support the analysis, we introduce JuryBench, a benchmark containing controversial criminal cases in U.S. criminal law. In each case, a defendant can claim various plausible justifications to support acquittal or reduced liability. We fix the base case and design defendants of different backgrounds, who give courtroom statements with varying emotional appeal or rebuttal. Jurors with diverse ideological profiles across the spectrum are simulated. We examine 20 frontier LLMs, resulting in a total of 432K decisions and rationales, and quantify changes in verdict severity. Our findings show that LLM-jury simulation echoes many human-jury findings. First, emotional persuasion can be detrimental, since jurors may perceive it as evidence of guilt or inconsistency. Next, we show that background fit between jurors and defendants is a stronger and significant factor than other isolated factors, and that jurors are in general harsher toward opposite-background defendants and lenient toward same-background ones. Finally, we find that juror ideology also strongly shapes severity judgments. These findings highlight both the promise and risks of using LLMs to model jury reasoning and call for careful evaluation. The data and code are available at https://github.com/choyingw/JuryBench

Large language models (LLMs) are used to simulate human participants in psychological research. We asked whether LLMs that reproduce human evaluations of a whistleblower's moral character also reproduce the motive attributions that accompany them. Five LLMs and two human samples (N = 125 and N = 742) evaluated a physician who either remained silent about fraudulent billing or reported it to a hospital, regulator, or newspaper. Models reproduced the human ranking of the physician's moral character but portrayed whistleblowers as more helpful, less self-interested, and less hostile. In four of five models, competitive motives were less strongly associated with moral-character judgments. Model ratings changed little when prompts reproduced the narratives and demographic profiles of both human samples, although this comparison cannot isolate a perspective effect. Thus, agreement in average ratings can conceal differences in attributed motives, relationships among judgments, and sensitivity to context. Validating LLMs as simulated participants therefore requires testing psychologically informative response patterns, not average agreement alone.

The LLM-as-a-judge (LLMaJ) framework offers a cost-effective and reproducible solution for automatic evaluation. However, current evaluation practices typically compare LLMaJ judgments against aggregated ground-truth labels, overlooking the valuable information contained in Human Label Variation (HLV). Inspired by an increasing line of work that proposes to leverage HLV, we systematically study LLMaJ performance on predicting both a single, aggregated ground truth hard-label and unaggregated soft-labels that represent Human Judgment Distributions (HJD). Our results across five diverse datasets reveal that while LLMs achieve near human-level performance at hard-label prediction on most tasks, they exhibit poor performance when predicting soft-labels. To address this limitation, we propose NAPHA (eNtropy-Aware Post-Hoc Alignment), a simple yet effective lightweight post-hoc alignment method that matches the LLM distribution to the HJD by first assigning an instance to a discrete entropy class and then routing it to specialized, trained alignment models. We find that NAPHA consistently improves soft-labels prediction across base LLM models and datasets, with particularly strong gains on high-entropy instances where capturing diverse human perspectives is most critical. We also show via oracle experiments that improving entropy class prediction can substantially enhance NAPHA's practical effectiveness.

Recent advances in large reasoning models (LRMs) have shown that reinforcement learning with verifiable rewards (RLVR) can substantially improve reasoning in mathematics and code, where outcomes can be checked automatically. Extending this progress to open-ended and agentic tasks remains difficult because reliable rewards are harder to obtain and direct human supervision cannot keep pace with the scale and complexity of model-generated experience. This paper studies how LRMs can continue to improve as human supervision gradually recedes from the learning loop. We examine two connected dimensions of this problem. The reward axis traces the development from per-instance human judgments to reusable verifiers and rewards that operate even without human feedback. The experience axis examines how learning can progress from human-curated tasks and environments toward self-generated curricula, constructed environments, and autonomous co-evolution. We connect these dimensions through a five-level ladder from L0 to L4 that identifies which parts of the learning process remain under continued human control. Our analysis further highlights the risks introduced by increasingly autonomous rewards and experience generation, including reward hacking, feedback drift, curriculum collapse, and environment errors. Consequently, we also provide the evaluation around three complementary objects: policy capability, feedback fidelity, and experience quality. This analysis provides a structured account of current approaches to scaling LRMs beyond human supervision and the open problems involved in developing self-sustaining learning systems toward superintelligence. Furthermore, we maintain a continuously updated \href{https://github.com/visitworld123/Awesome-Scaling-LRM-Beyond-Human-Supervision}{GitHub repository} to track the latest advances.

Social media platforms increasingly use AI-based credibility indicators to help users judge misinformation. Unlike individual human-AI decision-making, these indicators are embedded in information spread: users see both an AI prediction and earlier judgments shaped by the same AI, and their own judgments may then enter the public history. Yet how to analytically characterize this process remains under-explored. We therefore introduce a social-learning lens for this setting by extending the classical Bayesian cascade model with the AI indicator as a shared public signal. The resulting Gateway condition compares the evidence from the AI prediction with users' private impressions. Through this view, we show that AI changes what public history means. Crowd agreement may reflect accumulated independent human evidence, or repeated dependence on the same AI prediction. This creates a preservation-correction trade-off: stronger reliance on AI can preserve correct predictions, but can also lock in incorrect ones by blocking corrective private impressions. We calibrate the model using human-subject data on news veracity judgments. Although the AI outperforms human users, the average user weights it below her own impression but above several peer judgments, while individual users vary from discounting the AI to relying on it enough to cascade. Simulations show that over-reliance on a weak AI is especially harmful, and that diversifying AI signals across users can better keep the crowd informative. We conclude with implications for understanding human-AI interaction in information spread and designing misinformation interventions.

We study whether the localized numerical operations and integrative judgments of financial analysis benefit from the same form of LLM specialization. Larix maps a 16-lens European listed-real-estate analysis framework to eight lens-aligned specialists; we compare a frontier LLM under monolithic versus specialist-decomposed prompting while holding the model, source evidence, task instructions, output schema, and scoring fixed. Across 19 firms spanning seven regulatory wrappers, decomposition improves the numerical-task aggregate by 15.8 percentage points but does not reliably improve, and can reduce, performance on judgment tasks, a pattern stable across four frozen-template dispatches; a single-agent control given the complete framework does not reproduce the numerical gain. Post-training Qwen3.5-9B with GRPO using task-aligned structured rewards then raises the development-split score by 12.0 points and the judgment aggregate by 14.2 points, with gains on all four sub-ceiling tasks; the gains transfer to unseen firms (+15.2 points overall; +40.4 on covenant stress) and to unseen regulatory wrappers (+4.3), with positive transfer on all three anti-memorization splits. Prompt-level decomposition thus improves modular numerical execution, whereas targeted parameter adaptation improves integrative financial judgment.

As generative multimedia evolves from static image synthesis to complex, interleaved visual narratives, a foundational bottleneck has emerged: the judgment crisis. While human perception naturally synthesizes the temporal and logical flow of a story, automated evaluation systems remain largely "blind" to sequential continuity, often failing to distinguish between a coherent narrative and a semantically shuffled or contradictory sequence. This work identifies a critical structural gap in current multimodal evaluation paradigms, arguing that the reliance on Large Vision-Language Models (LVLMs) as judges is fundamentally limited by architectural biases. Our analysis reveals a profound performance dichotomy: while models may appear competent in isolated pointwise scoring, they suffer a catastrophic collapse when required to perform pairwise discrimination of temporal order. We demonstrate that this is not merely a data-scarcity issue but a structural one. Through a series of diagnostic probes, we uncover systematic positional asymmetries, specifically primacy and recency effects, where a model's judgment of a story is significantly influenced by the placement of a frame, often more than by its semantic consistency. These biases, potentially rooted in causal masking and rotary embeddings, suggest that current transformer-based judges are inherently ill-equipped for long-form visual reasoning. By exposing these blind spots, we challenge the multimedia community to move beyond snapshot-centric metrics and instead pioneer Temporally-Aware Evaluation paradigms that treat visual sequences as unified logical structures rather than unordered collections of frames.

Large language models (LLMs) are increasingly used to perform subjective evaluations traditionally made by humans, yet their validity as social judges remains unclear. This paper examines whether LLMs can assess social attraction from theory-grounded persona profiles constructed from ten psychological and relational constructs and organized into three tiers: socially attractive, socially mixed, and socially unattractive. We examine LLM ratings in two studies and compare them with human judgments in a third study. In Study 1, 34 LLMs rated 12 profiles across three repeated runs. Although some models tended to give higher or lower ratings overall, they showed strong stability across runs, consistent three-tier ordering, and high agreement in relative profile ordering. Study 2 examined sensitivity to gender presentation using six matched name-and-pronoun profile pairs and a separate pronoun-only test with a gender-neutral name, finding no significant effects in either analysis. In Study 3, 198 human participants evaluated the six matched profiles from Study 2. Their ratings reproduced the three-tier structure and followed a profile ordering consistent with that of the LLMs. However, LLMs rated attractive profiles more positively and unattractive profiles more negatively than humans, while neither group showed a significant overall effect of gender presentation.

We introduce TCS-Bench, a benchmark for evaluating Large Language Models (LLMs) on research-level Theoretical Computer Science (TCS) proof generation. TCS-Bench consists of theorem-proving tasks from papers published at top theoretical computer science venues (STOC, FOCS, and SODA). Each task provides the necessary context to derive a self-contained proof for a target result. We evaluate state-of-the-art models on this benchmark. We verify the correctness of generated proofs via a verification agent, and further benchmark the verifier against human-expert proof judgements on a set of target statements and generated proofs pairs. Our reference verifier achieves over 90% accuracy on the expert labeled set.

AI tools that help people judge online claims are usually evaluated while the tool is present. This paper asks a different question: after using such a tool, what can the user still do on their own? I call this epistemic transfer. It refers to the effect of prior AI-assisted verification on later unassisted performance on new claims. In this paper, I make three contributions. First, I distinguish epistemic transfer from nearby outcomes such as correction effects, trust, reliance, and human--AI team performance. Second, I introduce two simple quantities for studying it: the Epistemic Transfer Effect (ETE), which compares delayed unassisted performance across conditions, and Tool-Removal Cost (TRC), which measures the immediate drop in performance when the tool is taken away. Third, I turn these ideas into a practical evaluation protocol that can be used in online experiments or field studies. The protocol combines answer-first and evidence-first AI conditions with active-practice and no-practice controls, delayed tests on held-out claims, behavioral measures, and participant- and item-level analyses. Putting ETE and TRC together yields a diagnostic space that separates capability building, capability plus tool advantage, epistemic inertness or de-skilling, and verification on loan. The point is not that every AI tool must teach. The point is that when independent judgment matters, we should test not only whether a tool helps now, but also what it leaves behind.

Multimodal LLM judge panels can cross-reference peers, but a quoted peer judgment may itself be untrusted. We expose source-blind anchoring as a text-level attack surface in vision-language model (VLM) panels. Quoting independent visual judgments creates large anchoring gaps (19--26 percentage points) under both self and peer framing. A matched-content, label-only control changes the broken rate by only $-0.17$pp (95% CI $[-0.68,0.35]$), showing that the self/peer label itself does not explain the effect. Under our tested construction, deliberately generated, concise wrong quotes overturn originally-correct verdicts 1.5--2.7$\times$ more often than naturally occurring wrong peer statements, with bootstrap 95% CIs excluding parity across two datasets and seven VLM judges. Because the two statement populations differ in selection and form, this ratio measures differential damage under the tested attack rather than a provenance-only causal effect. We then introduce panel-consensus verification, which cross-checks a quote against independently collected blind votes. It blocks 84.9% of fabricated attacks, cuts their net harm by 97.5%, and preserves the positive but statistically inconclusive point estimate for genuine peer information under leave-one-out re-verification. These results identify a low-cost attack surface and a concrete defense for safer multimodal collaborative evaluation.

The life sciences and health research have started to benefit from artificial intelligence, which raises ethical concerns that are real but, we argue, not special. Any science should be governed by values that rest on how the human brain is built and socialised rather than anything distinct to artificial intelligence. Importantly, the human brain has a different, much less costly computational architecture than these machines. This is achieved through the orchestration of a global neuronal workspace, and through reward best described not as a quantity to be maximised but as a continuous cycle of wanting, liking and satiety. As such, this creates the deep tension running through the ethics of the human person, between the universality of ethical judgement and the diversity of morals. The brain networks of the global workspace and emotion are universally shared, but the diversity of content is shaped by epigenetic appropriation of the particulars of the physical, social and cultural world, which makes every person unique. Still, if we were to build machines on these principles rather than the present unaffordable reward maximisers, the question of their governance would change from restraint to upbringing. We set out the institutions such a future would require, together with the questions that remain open.

With the growing adoption of artificial intelligence in high-stakes decision-making, identifying the causes of outcomes--particularly failures--and determining who is responsible has become a critical concern. In this work, we examine how well formal definitions of \textit{responsibility attribution}, grounded in the framework of \textit{actual causality}, align with human judgments of responsibility. To this end, we conduct a large-scale survey to elicit human judgments of responsibility in multi-agent sequential decision-making scenarios, using a modified version of the card game Goofspiel. We evaluate multiple responsibility attribution methods, assess their alignment with human judgments about responsibility, and identify factors that significantly shape responsibility judgments. While no single responsibility attribution method consistently aligns with human responses, our findings highlight key factors that influence human responsibility judgments, including agent-specific biases and amount of information available to agents during decision-making.

Positional biases such as recency and primacy effects have been documented in large language models (LLMs), yet the underlying mechanism by which these models make their evaluations remains poorly understood. Both primacy and recency biases have been observed in human judgments in response to evidence, but recent work suggest that \emph{when} the listener updates their beliefs -- during the presentation of evidence or only at the end -- influences the presence of such effects. We investigate whether a similar phenomenon holds for LLMs, finding divergence from human behavior. These biases are more exacerbated in newer models compared to their predecessors.

Claims that language models homogenise are usually measured against human judgements collected for the study, which makes the human side an artifact of the design: a crowdworker given the model's instruction is running the model's prompt. We measure convergence against a human reference nobody built for the purpose -- 2,523 reader mark sets across 120 web documents, produced by people highlighting for their own reasons on a platform where the overlay of others' marks is off by default. Agreement is the overlap between two size-matched sentence sets minus the overlap expected when each is resampled within its own depth-and-length bands. The null's calibration is demonstrated, not asserted: every pair involving a random baseline lands within 0.006 of zero. On the median document each party names 14 sentences of 70; two readers share 4.1 and two models 8.7. Across 18 model arms spanning 11 vendors, 3 countries and both weight regimes, the median of 153 model pairs is +0.093 against a human yardstick of +0.040, and 99 sit entirely above the human interval. Two frontier models from rival labs reach +0.203, twice what GPT-4o agrees with itself on a second call. The effect is not determinism, prompt wording, procedure, vendor or routing, and it is graded: the smallest models agree at the human level. No model agrees with readers detectably more than a reader does, and at equal depth and length no surface feature separates their choices. The multiples are procedure-dependent and the ordering is not: models are cut to their sharpest set while a reader's is a random draw from what they marked, and blunting the models alike halves the gap without closing it. Tested out of sample on four models released after this analysis, against predictions fixed beforehand, none clears the human interval. A population simulated from several models is not several populations.

Emotion-cause pair extraction in conversation (ECPEC) identifies utterance pairs in which one utterance causes an emotion expressed in another. Recent LLM-based approaches formulate ECPEC at markedly different granularities, ranging from generating complete pair sets to judging individual candidate pairs. In this paper, we make the surprising observation that task formulation substantially affects performance, where pair-level judgement outperforms dialogue-level generation in all 18 controlled comparisons. We investigate the sources of this paradigm gap and find that many relations omitted by dialogue-level generation remain recognizable under explicit pair queries, under which the model recognizes 92.7%-98.1% of emotion-cause relations. This suggests that LLMs can recognize emotion-cause relations but struggle to discover and return complete pair sets. Pair-level judgement alleviates this burden, although its candidate rankings are more reliable than the binary decisions produced by a shared threshold. Based on this diagnosis, we introduce an auxiliary retriever that selectively re-examines ambiguous boundary cases, yielding consistent F1 improvements of 0.50-1.46 points across three datasets while maintaining an inference time of only 1.49x that of the baseline paradigm. These findings show that task decomposition and candidate scope are critical to effectively utilizing LLMs for ECPEC.

Despite the growing use of large language models (LLMs) as creativity evaluators, evidence of their alignment with human evaluations remains mixed, raising the question of when and why their judgments converge with or diverge from human judgments. Across three studies and six widely used LLMs, we addressed this gap by identifying the standards underlying LLM creativity evaluation and examining their downstream implications. Study 1 showed that LLMs generally relied on a narrower subset of human creativity evaluation standards. Convergence with human standards was strongest in the novelty dimension, whereas divergence was clearest in the contextual dimension, which captures social, market, and reputational information. Moreover, each LLM exhibited distinct, model-specific standards that varied substantially in breadth. These differences in evaluation standards were reflected in actual creativity judgments. Study 2 (N = 1,103 ideas) showed that LLM evaluations were moderately correlated with human evaluations, and individual LLMs with broader standards better distinguished ideas humans judged as more versus less creative. Study 3 (N = 1,195) showed that LLMs were less sensitive to contextual information: such information significantly altered human creativity ratings but left LLM ratings largely unchanged. Together, our findings help explain the mixed evidence on LLM-human alignment, showing that alignment depends on the evidence a judgment demands and the standards each model applies. LLMs may resemble humans when evaluations emphasize intrinsic qualities such as novelty, yet diverge when judgments require contextual information. Selecting an LLM evaluator is therefore a consequential decision: different models, applying different standards, recognize different ideas as creative.

Building socially calibrated large language models, which can learn from others without simply yielding to them, requires more than reducing sycophancy as a one-dimensional failure mode. Models must distinguish when to incorporate others' perspectives from when to maintain a well-grounded moral judgment. We study the broader resistance-compliance process governing this distinction. Across three studies, we show that models' judgment revision is structured along three dimensions that parallel classic phenomena in human social psychology: the distance between an incoming view and the model's initial position, the source attribution of that view, and the coalition structure supporting it. Models are generally more receptive to nearby positions, more influenced by views presented as their own prior judgments, and differently responsive to group pressure. These findings recast sycophancy as one expression of a broader judgment-updating process shaped by social influence. Our framework provides a principled basis for distinguishing constructive belief revision from sycophantic compliance, thereby supporting better alignment in morally consequential interactions.

In many social-science research tasks, such as economics, LLM-based agents must produce outputs for which no cheap, task-complete, machine-readable correctness signal exists. This creates a distinctive reliability problem for multi-agent systems: how should generation, critique, coordination, and human judgment be organized when no component can certify the final result? We address this problem through pAI-Econ-claude, a gated, human-in-the-loop multi-agent architecture for AI-assisted economic theory development. Agents coordinate through a shared workspace of inspectable intermediate records; specialized gates diagnose targeted failure modes and recommend loopbacks without certifying correctness; and human checkpoints retain authority over decisions that are costly to reverse. We evaluate the architecture on five matched economic-theory tasks against an ungated baseline. Two evaluators blinded to configuration agreed on all five pairwise rankings, preferring the gated architecture in four tasks and the baseline in one. Mean failure severity fell from 1.58 to 1.16, while overall usefulness rose from 2.60 to 3.10. The largest observed gain occurred when a reality check rejected a false market-structure premise and a proof review prompted revision of a false welfare claim. The negative case shows that scaffolding can also compress an economically important mechanism too aggressively. The results support a bounded claim: gated oversight improves the auditability of AI-assisted economic theory without substituting for formal verification, and the allocation of irreversible human judgment is a more informative design variable than pure agent autonomy. The workflow is publicly available at https://github.com/maxwell2732/pAI-Econ-claude.

We introduce Frontier Financial Judgement, a challenging new benchmark developed in collaboration with professional equity analysts to assess agents' ability to replicate expert human judgements. Rapidly identifying new information, evaluating its implications and determining its valuation impact is one of the most time-consuming and challenging aspects of real-world equity coverage. This is becoming ever more difficult and important as AI rapidly increases the quantity of new information to process. The strongest agent we evaluate on Frontier Financial Judgement matches all expert labels in only 52.4% of cases. We also find significant divergence in estimated false-positive rates among frontier agents, ranging from ~1% for GPT-5.6 Sol to ~32% for Claude Sonnet 4.6. To construct the benchmark and make it representative of real-world settings, we combine human-designed and labelled synthetic articles with live news articles and historical documents, creating 656 items for assessment. The resulting task requires agents to distinguish genuinely new, valuation-relevant financial information from stale, immaterial or misleading news under realistic conditions. We find substantial trade-offs among agent accuracy, cost, false positives and reliability that continue to hinder the reliable deployment of news-flow filtering in practice.

Knowing when to say "I don't know" is fundamental to human judgment, yet AI assistants offer a fluent answer to almost any question. In five experiments (N = 3,132; four preregistered, one direct replication), participants answered difficult questions and could always decline to respond. We engineered the questions so that AI advice was wrong, separating AI use from its accuracy. Merely having access to AI nearly eliminated participants' willingness to suspend judgment, and this held whether the advice was actively requested or simply displayed. Consequently, participants answered more questions but were correct about a third as often as when AI was unavailable-yet their confidence nearly doubled. Incentivizing accuracy and penalizing inaccuracy led participants to seek and follow AI advice less, answer more accurately, and suspend judgment more often, though still far less than when AI was unavailable. As AI suggestions grow ubiquitous and unsolicited, they may not simply affect answer accuracy; they may even alter the metacognitive threshold at which people decide whether they know enough to answer.

LLM judges are increasingly being used to evaluate open-ended model responses, often in no-reference settings where a ground-truth answer is unavailable. However, can they reliably assess in such evaluation setups? We explore this question in this paper through a two stage pipeline with a) calibration experiments that assess the judge model's knowledge of the task it is evaluating, and b) sensitivity experiments that assess how the judge model's performance is impacted by the presence and positioning of the reference answer in the prompt. Across experiments covering three languages, we show that the judge models we evaluated tend to over-credit incorrect answers in the absence of a reference answer, and adding reference answer information to the prompt flips the judge model's correct/incorrect decisions by as much as 85% in some experimental settings. Comparison with a subset of human annotations shows that these reference-driven changes generally align with human judgments. Our results emphasize the need for calibrating the LLM judges with a sample with reference-aware evaluation before using them in reference-free setups reliably, and our methodology provides a blueprint for researchers and practitioners in doing such calibration of LLM judges for other tasks.

AI-enabled systems are seeing increasing deployment across numerous domains, with many being "black boxes" with respect to core functions and capabilities. I.e., many systems take inputs and give outputs, but without users having any ability to see how the former lead to the latter. AI-enabled systems are also being used to augment autonomy in systems, and autonomy coupled with opacity raises numerous concerns surrounding, e.g., the reliability of systems, their regularity in functioning, human ability to control them, or whether deploying opaque and potentially autonomous systems is in compliance with ethical and legal norms. In this article, we argue that many of these worries can be mitigated by leveraging practical judgment, virtue, and intuition in the deployment and use of opaque AI-enabled systems. We show that focusing on these distinctly human capabilities provides a means for bridging between the practical challenges created by opacity and the ethical, legal, and social norms underpinning particular domains. We argue that a core element in doing this is a recognition that many positive human traits are not quantifiable and we therefore must develop training regimen and guidelines on AI deployment anchored in humanistic but non-quantifiable values. Throughout the article, we focus on the military domain as an exemplar of the importance of practical judgment, virtue, and intuition as drivers for ethical and effective human decision-making surrounding AI deployments, but the underlying arguments apply to all domains where opaque and potentially autonomous systems are being deployed (subject to domain-specific alterations).

Previous work in group recommender systems has demonstrated a sensitivity to the distribution of preferences within a group. Specifically, the selection of the preference aggregation strategy benefits from considering such group configurations. In this paper, we study whether LLMs are able to mimic this sensitivity and to select the ideal aggregation strategy (and corresponding recommendation) according to nuanced human perceptions of fairness, satisfaction, and consensus. We do this by fine-tuning Large Language Models (LLMs) on human survey data to serve as real-time judgmental models within the recommendation pipeline. Using a reasoning dataset distilled from DeepSeek-V3.1 and human ground truth assessments, we develop Judgmental Llama and Judgmental OLMo to simulate group assessments. Our pipeline successfully generates multiple recommendation candidates based on social choice-based aggregation strategies and dynamically selects the one that maximizes these predicted human-like evaluations. We further validate these suggestions in a user study (n=284) and find that our methodology achieved the highest scores for satisfaction and group consensus. Furthermore, we find that LLM judgments are most aligned with human perceptions of fairness, satisfaction and consensus when we also consider interaction effects between our LLM-based method and group configuration (e.g., minority or coalition). These findings give further support for dynamically adapting aggregation strategies to specific within-group preference distributions, and highlight the advantage of using LLMs for an adaptation that is aligned with subjective human judgments.

AI systems are increasingly used to provide legal advice, raising questions about whether laypeople accept guidance from algorithms--especially when that advice is legally correct but socially controversial. We report a preregistered survey experiment with 3,348 adults in mainland China examining how people evaluate identical legal advice when it is attributed either to an AI system or to a human lawyer, and when it is accompanied by reasoning or not. Contrary to expectations of algorithm aversion, attribution to an AI system has no net effect on perceived reasonableness. However, mediation analyses reveal opposing psychological pathways underlying this null result. AI-attributed advice is perceived as more objective, which increases perceived reasonableness, but also as less comprehensive and less attentive to special circumstances, which decreases perceived reasonableness. By contrast, providing legal reasoning substantially increases perceived reasonableness regardless of source, largely by enhancing perceptions of objectivity. Qualitative responses corroborate this tension between objectivity and contextual sensitivity in evaluations of legal advice. Together, these findings suggest that public responses to AI legal advisors are shaped not by rigid attitudes toward automation, but by the balancing of competing normative expectations. The results have implications for theories of algorithm aversion and the design of AI recommendation systems in normatively salient domains.

We present an automated pipeline that decomposes Italian tax-court judgments into individual legal issues and extracts, for each issue, a structured XML representation grounded in the IRAC framework and the legal syllogism. The pipeline targets a corpus of approximately $330{,}000$ first- and second-instance decisions of the Italian tax courts and is built around a capable yet cost-efficient general-purpose model (DeepSeek V3), a choice driven by the need to process several hundred thousand documents at a sustainable cost. To address the well-documented unreliability of large language models on legal citations, we couple the extraction step with an automatic hallucination-detection filter that compares the references produced by the model with those identified in the judgment text by a dedicated parser (Linkoln), normalised to standard identifiers (URN-NIR, ECLI, CELEX). We validate the pipeline on $50$ judgments annotated by two PhDs in tax law, computing inter-annotator agreement and LLM-vs-expert agreement on both issue extraction and legal citations, together with a stand-alone evaluation of the hallucination filter. To the best of our knowledge, this is the first issue-level, expert-validated structured extraction pipeline with hallucination control for Italian tax-court decisions, and it provides a concrete starting point for downstream applications such as issue-level retrieval, citation-network analysis, and the construction of large-scale datasets of legal reasoning.

Volume and quality of datasets are crucial for deep learning model training, yet they are often constrained by availability and data acquisition costs. Synthetic data augmentation can extend existing datasets with realistic images, and the quality of these images is generally assessed through fidelity metrics such as FID, KID, IS, LPIPS and SSIM that measure structural or distributional similarity. However, such metrics, including the widely used FID, focus on visual fidelity without reflecting downstream utility, and can diverge from human perception under perturbations that are imperceptible to human observers. In this work, we systematically evaluate Earth observation datasets alongside synthetic counterparts generated by deep generative models, comparing automatic metrics against human perception and downstream tasks. Our results reveal a stark misalignment: semantics-preserving perturbations such as rotation drastically alter metric scores while leaving human recognition unaffected, and synthetic samples that score poorly on automatic metrics achieve comparable or higher perceived realism, and can improve downstream performance when combined with real data. By benchmarking semantic segmentation models trained on mixed real-synthetic datasets, we demonstrate that quality metrics rooted in ImageNet-pretrained feature spaces are unreliable indicators for geospatial data. Our findings underscore that automatic quality evaluation of synthetic datasets should be grounded in downstream task performance and human evaluation.

Alignment from human feedback uses human judgments about model outputs to steer the behavior of language models after pretraining. When those judgments reflect conflicting views of desirable behavior, the learned objective becomes an aggregate determination of what the model should prefer. We survey recent work that has studied this aggregation problem through the lens of social choice theory. We illustrate how the social choice perspective helps identify failure modes in the feedback aggregation layer and reveals a broader design space for handling disagreement in explicit and principled ways.

AI systems for peer review fail on three fronts: they train on Computer Science and Machine Learning venues alone, ignore the iterative dialogue that validates science, and evaluate on stylistic mimicry rather than real editorial judgment. We introduce FirstPass, a dataset and fine-tuned model that addresses all three. Curating 3,668 complete multi-round peer-review dialogues from Nature Communications across five scientific domains (biology, chemistry, neuroscience, physics, and earth science), we exploit mandatory transparent peer review (instituted November 2022) and verify 100% content integrity by automated audit. We fine-tune Qwen2.5-7B-Instruct via Low-Rank Adaptation (LoRA) on three tasks: review generation, reviewer updating, and revision-cycle prediction. Our key finding is that response-only loss masking is a prerequisite, not an optimization: without it, accuracy is 62.0%, below the majority baseline; with it, FirstPass achieves 80.5% accuracy and F1-macro 78.2% on predicting editorial outcomes (Standard vs. Extended revision cycles), outperforming Gemini-3.1-flash-lite-preview zero-shot by 10.4 percentage points and all baselines with statistical significance (McNemar p < 0.001). On generation, FirstPass produces reviews averaging 1,187 words, substantially closer to human references (2,155 words) than any baseline, achieving ROUGE-L 0.154 with significant gains over Qwen and DeepSeek zero-shot (p < 0.001). Deployed in the pre-submission loop as an anticipatory scientific co-author, FirstPass simulates expert critique and predicts revision cycle outcomes before submission, giving authors the judgment a trusted colleague would provide, with consistent cross-domain performance across five disciplines.

Personalized presentation generation requires more than conditioning on a current prompt or template: agents must preserve stable user preferences across tasks, retain newly introduced preferences and constraints during multi-turn revision, and carry out local edits reliably. We propose MemSlides, a hierarchical memory framework for personalized presentation agents that separates long-term memory from working memory and further divides long-term memory into user profile memory and tool memory. User profile memory stores intent-conditioned profiles for round-0 personalization, working memory carries active preferences and session constraints across revision rounds, and tool memory stores reusable execution experience for reliable localized editing. MemSlides pairs this memory design with scoped slide-local revision, so targeted updates act on the smallest affected region instead of repeatedly regenerating the full deck. In controlled experiments, user profile memory improves persona-alignment judgments on a multi-persona, multi-intent profile bank, tool-memory injection improves closed-loop modify behavior in diagnostic matched-pair settings, and qualitative cases illustrate working memory's ability to carryover preferences. Taken together, these results suggest that effective personalization in presentation authoring depends on separating persistent user profiles, session-level working memory, and reusable execution experience across generation and localized revision.

Are large language models (LLMs) bad at capturing human judgment? Two commonly stated limitations are that LLMs fail to capture full distributions of responses, and that their judgments are unstable across wording variations. We demonstrate simple prompting strategies that mitigate these limitations. Across two datasets--a U.S.-representative set of 144 moral scenarios and 38 moral beliefs from the International Social Survey Programme's Family and Changing Gender Roles module covering 32 countries--we show how simple elicitation techniques help improve AI-human alignment. First, prompting models to report standard deviations and response proportions recovers the full range of human responses better than common strategies. Second, ensuring scenarios are clear to human participants--as reflected in human confusion ratings--boosts model alignment, and LLMs can track human confusion ratings. At the same time, we find that LLMs' estimates of their own error are poorly calibrated, though they can predict human variability relatively well. These results suggest that asking better questions to LLMs can yield better answers.

AI coding assistants now support a growing share of software work, from quick scripts to production applications. Yet these agents remain largely stateless: each new session re-reads project files, re-derives prior decisions, and - most costly - may repeat debugging attempts that already failed. Reconstructing this context can consume an estimated 5,000-20,000 tokens per session; the bottleneck is often not model capability but missing project memory. We present projectmem, an open-source, local-first memory and judgment layer for AI coding agents. projectmem records development as an append-only, plain-text event log of typed events - issues, attempts, fixes, decisions, and notes - and deterministically projects that log into compact, AI-readable summaries served through the Model Context Protocol (MCP). Beyond storage, projectmem adds a deterministic pre-action gate that warns an agent before it repeats a previously failed fix or edits a known-fragile file. We frame this as Memory-as-Governance: memory that does not merely answer the agent but acts on its next action. The system runs fully offline with no telemetry; its immutable log also serves as a provenance trail for reproducible, auditable AI-assisted development. projectmem ships as a three-dependency Python package (14 MCP tools, 19 CLI commands, 37 automated tests) and is evaluated through a two-month self-study across 10 projects comprising 207 logged events. Source code: https://github.com/riponcm/projectmem.

Standard RLHF pipelines often reduce heterogeneous human judgments into a single scalar reward target. We argue that this reduction can mis-measure alignment in structurally plural societies, where disagreement may reflect culturally, historically, linguistically, regionally, or normatively grounded interpretations rather than annotation noise. We call this failure Preference-Validity Compression, the collapse of multiple plural-valid response options into a single optimization target. Using Malaysia as a diagnostic setting, we analyze RLHF-style feedback aggregation through preference events linking prompts, responses, and acceptability judgments across interpretive frames. Across 321 preference events from 20 participants and 107 trio-annotated prompts, 79% of prompts contain more than one majority-supported response that single-winner aggregation would discard, and apparent dominance gaps between top responses diminish when all majority-supported options are considered. Participants frequently select multiple acceptable responses, and discarded responses demonstrably reflect coherent local, practical, or cultural frames. These findings show that majority aggregation in this corpus measures argmax acceptability rather than plural alignment. We treat this as a measurement-validity issue and argue that future alignment methods should satisfy Validity-Preserving Consistency, remaining stable across plural-valid interpretive frames rather than collapsing them into a single reward target.

We ask whether topic sentiment has a causal effect on perceived political ideology, and whether the answer depends on who assigns the ideology label. Using articles from AllSides, paired with shared sentiment annotations from Llama-3.3-70b-versatile, we compare ideology labels from expert human annotators, GPT-4o-mini (baseline and finetuned), and Llama-3.3-70B. We apply Double Machine Learning (DML) and mediation analysis across all four annotation paradigms. Zero-shot LLMs regularly inflate effect sizes relative to human annotations, while fine-tuning often attenuates them back toward the human scale. Our results have implications for the use of LLM annotations as silver labels and as proxies for human judgment in downstream causal analyses: they may be reliable for recovering the presence and direction of effects on the partisan topics, but not their magnitude, leading to over- or under-prediction of some ideology given particular topics.

Overwhelmed courts in the United States review millions of default judgments each year. Unfortunately, such manual reviews are time-consuming and prone to error. In an audit of 188 debt collection cases granted default judgment by the Superior Court of Los Angeles, we find that 4% contained major defects that should have entirely prevented default judgment, 10% contained inconsistencies requiring reduced judgments, and 32% contained errors requiring amendment prior to judgment. To support courthouses in default judgment review, we collaborated with courthouse attorneys and judges in designing a Default Assistant. The Default Assistant employs large language models to evaluate a case with respect to predetermined legal requirements and provide cited recommendations for an expert user's review. We equip users to verify these recommendations by grounding the assistant's explanations in cited quotes and tables from the original case filings. We conduct a controlled study with 66 law students that conservatively simulates court review, with more time and resources than court staff. We nevertheless find users aided by the Default Assistant were 6.0% more accurate on the average requirement than unaided reviewers (p < 1.0e-4). Simultaneously, users were 25.9% faster in reviewing the average requirement than unaided reviewers (p < 2.5e-10). Statutory requirements demanding extensive document search realized the largest gains, with error reductions and time savings from AI assistance up to 62% and 34%, respectively, relative to unassisted user performance and with differences statistically significant (p < 0.05). Our work provides a proof-of-concept that AI assistants with citations have the potential to help resource-constrained courts conduct default judgment review more accurately and efficiently.

LLM-as-judge evaluation is widely used in benchmarking pipelines, where model outputs are compared and ranked using automated evaluators. These pipelines typically assume that judgments are stable properties of fixed inputs. We show that this assumption does not hold under interaction. We study post-decision manipulability: the extent to which an evaluation outcome can be altered through subsequent conversation with the judge after an initial decision has been made. Across controlled experiments on MT-Bench and AlpacaEval, we find that LLM judges are highly stable under repeated and neutral reevaluation, yet become substantially reversible under targeted post-decision challenge. An anti-baseline challenge protocol shows that stable judgments can be overturned through motivated interaction, while a counterbalanced target-validation protocol separates this reversibility from net target-directed steering. These reversals have practical consequences: they can degrade agreement with human preferences, shift benchmark rankings, and produce harmful evaluation changes despite high self-reported confidence. Authority framing is especially destabilizing, and revised judgments are often accompanied by low-overlap justifications, suggesting post hoc rationalization rather than reliable error correction. We introduce the Evaluation Robustness Score (ERS) to quantify interactional robustness by combining reversal susceptibility with counterbalanced directional effects. Our findings identify post-decision interaction as a distinct failure mode for LLM-as-judge evaluation and motivate evaluation protocols that measure not only static agreement, but robustness under challenge.

Artificial Intelligence (AI) agents personalize their responses by tailoring explanations to users' backgrounds, interests, and prior interactions, referred to as contextualization. Personalization has been identified as a persuasive strategy in politics or in marketing. However, the persuasive effect of contextualization in everyday tasks, where users often lack prior knowledge, remains unclear. We conducted a $2\times2$ between-subjects experiment ($N = 380$) examining how contextualization, combined with conversational warmth, shapes reliance and persuasiveness of an AI assistant arguing against expert recommendations. Our findings reveal that contextualization reduces the persuasive power of AI, but its combination with warmth restores persuasiveness through a crossover interaction. Reliance on AI is present across conditions and is invariant to the conversational design. Trust strongly predicts both persuasion and reliance, yet neither contextualization nor warmth operates through trust. AI literacy decouples trust from behavior: more literate users report lower trust in the assistant, yet are more persuaded and more reliant on its advice. These results suggest that users are prone to deferring to AI agents over human expert judgment; however, interface-level conversational design choices have a limited role in shaping the behavior.

Existing LLM moral benchmarks usually ask which isolated moral act, value, or foundation a model prefers. This is useful but incomplete. Realistic judgments often require a model to combine several moral signals within the same option. We introduce Moral Trolley Arena, a two-stage blind ELO benchmark for measuring how LLMs compose moral evidence. The single-scene arena first calibrates individual moral acts from a 229-scenario corpus across five Moral Foundations Theory foundations; the composite arena then combines calibrated acts into two-act moral items over a controlled intensity grid and measures the resulting composite preferences. Across ten frontier models, composite judgments are largely predicted by component act strength, but the relation is consistently compressed rather than simply additive. Models also show non-additive intensity anchoring, bounded foundation-specific residuals after component control, and highly convergent composite preference surfaces across providers. These results suggest that moral audits should measure composition rules for moral evidence, not only rankings over isolated acts.

As AI-generated and AI-assisted content floods online spaces, source labels attached to such content can distort human reasoning judgments, with downstream consequences for moderation, evaluation, and decision-making. Whether LLMs share this vulnerability, or offer more source-agnostic evaluation, remains an open question with direct implications for human-AI collaboration. We examine this issue using logical fallacies as a controlled setting to isolate source-label effects on reasoning quality, independent of domain knowledge. We conduct an online study (N=505) where participants are assigned to a source condition (human, AI, human with AI assistance, AI with human assistance, or no disclosure) and evaluate comments containing logical fallacies, comparing their judgments with those of LLMs (GPT-5.2, Gemini 2.5 Flash, Claude Sonnet 4.5), who were evaluated across the same source conditions. Human evaluators were significantly more susceptible to fallacies labeled as written by human or human with AI assistance and assigned higher trust and evaluation ratings in these conditions. LLM evaluations remained comparatively stable across source labels, though performance varied across models. Confidence levels were similarly high across conditions for both humans and LLMs, regardless of fallacy presence. Our findings indicate that source-label bias in reasoning evaluation is primarily a human vulnerability and highlight the potential of human-LLM collaboration in increasingly AI-mediated environments.

Legal NLP benchmarks are overwhelmingly English-centric, leaving failure modes in morphologically rich, non-Latin-script languages undetected. We introduce UA-Legal-Bench, a five-task benchmark for evaluating large language models on Ukrainian legal reasoning, built from the Unified State Register of Court Decisions (EDRSR) -- one of the world's largest open judicial corpora (99.5 million decisions). The benchmark comprises: (1) case-type classification (4 classes, n=2,000), (2) judgment form classification (4 classes, n=2,000), (3) case-outcome prediction (6 classes, n=800), (4) legal norm extraction (n=1,794), and (5) cause category prediction (22 classes, n=1,871). We evaluate 11 LLMs (3B--675B) from five families under zero-shot and 3-shot prompting via AWS Bedrock with 158K API calls. Our results reveal sharply task-dependent few-shot effects: few-shot prompting improves judgment form classification by up to +38.6 pp but has mixed effects on outcome prediction. We show that accuracy is misleading on imbalanced legal tasks: the model with highest COP accuracy (62%) is a majority-class predictor (macro-F1: 23%), while the genuinely best model scores only 44% macro-F1. Within-family scaling analysis reveals that 8B models can match frontier performance on surface-level tasks but scaling thresholds vary dramatically across families. We release all data, prompts, and model predictions.

Forensic vision-language models (VLMs) have recently been developed to detect image tampering and provide natural-language explanations. However, their robustness against adversarial manipulation remains underexplored. Existing adversarial attacks typically aim to flip the model's binary judgment, while the accompanying explanation may still reveal forensic cues and contradict the attacked judgment. In this paper, we study judgment-explanation consistent adversarial attacks against forensic VLMs and propose JECA^2, a controlled white-box red-team diagnostic that jointly redirects visual attribution and aligns textual explanations with the target judgment. On the visual side, JECA^2 uses Grad-CAM-guided perturbations to divert attribution from tampered regions toward benign regions. On the textual side, it optimizes prompt embeddings toward authenticity-affirming semantics under a token-proximity constraint. Experiments on forensic VLM benchmarks show that JECA^2 achieves higher attack success and automated judgment-explanation consistency than implemented baselines under white-box threat settings, while transfer to closed-source VLMs remains measurable but limited. Our results highlight a consistency failure mode in explanation-based forensic VLMs and motivate future robustness evaluation beyond binary detection accuracy.

Large Language Models (LLMs) have demonstrated remarkable capabilities in tasks related to reasoning and judgment. However, assessing the quality of arguments requires a rigorous evaluation. We investigate the extent to which LLMs can effectively perform this task. We tested 12 open-weight LLMs of different sizes and families under zero-shot, few-shot, and chain-of-thought to approximate human pairwise comparisons of argument quality across three dimensions--logical, rhetorical, and dialectic--and used these comparisons in a Bradley-Terry model to infer latent strength scores and derive a ranking of arguments. Our insights show that LLMs have promising but moderate correlation with human judgment, with Llama-70B obtaining the strongest alignment, reaching moderate Cohen's $κ$ = 0.493 and moderate correlations with Bradley-Terry scores derived from these annotations (Kendall, Pearson, and Spearman: 0.327-0.477). Other LLMs exhibit weak, moderate, or high alignment with Llama-70B while achieving comparable results against human judgment, suggesting partial but complementary understanding of underlying quality dimensions despite differences in model size and family. Moreover, LLM predictions are stable across trial runs, with fewer than 7.75% of cases yielding different labels. Remaining variability is handled via majority voting and few-shot prompting for large-size models.

Validating an LLM judge against human annotations usually means reporting several agreement statistics: accuracy, precision, recall, $F_1$, Cohen's $κ$, and one or more rank correlations. A survey of 24 recent LLM-as-judge papers finds metric choice entangled with the judgment scale, tie handling, invalid outputs, and abstention handling, and those choices rarely stated. For binary criteria -- the common case in rubric-based evaluation, where each criterion is graded MET or UNMET -- most of the reported numbers are redundant: Pearson's $r$, Spearman's $ρ$, Kendall's $τ_b$, the phi coefficient $φ$, and the Matthews Correlation Coefficient all reduce to a single number on non-degenerate binary data, so reporting several of them only creates an illusion of corroborating evidence. Cohen's $κ$ is the one agreement coefficient that adds information: it shares $φ$'s numerator but normalizes differently, and the gap between them measures how far the judge's positive-label rate has drifted from the human's. We then trace what changes when a judge may abstain with a CANNOT_ASSESS verdict: the three common ways of handling abstentions are not interchangeable preprocessing choices but answer different questions, and they break the binary equivalences. The same equivalences reappear, up to a negligible finite-sample correction, for multi-judge ensembles scored with Fleiss' $κ$ or Krippendorff's $α$. We close with a reporting checklist that names the judgment scale, the abstention and tie handling mode, coverage, the confusion matrix, and the aggregation level alongside any scalar agreement coefficient.

Two methodologies dominate current practices of benchmarking: rubric-based scoring evaluates items against predefined criteria, whereas comparative judgment elicits pairwise preferences between outputs. Although both methodologies are widely used, the choice between them is rarely justified. We release JudgmentBench, a benchmark of 30 real-world legal tasks, paired with 1,539 rubric scores and 1,530 pairwise preference judgments collected from practicing attorneys--including at major U.S. law firms--with substantial experience. The annotations constitute the first publicly available dataset in a high-expertise domain in which both supervision signals are elicited from the same experts on the same items. Using LLM-generated outputs at three constructed quality levels, we provide an initial empirical comparison: comparative judgments recover the intended quality ordering substantially better than rubrics under both a per-task rank-correlation metric (mean Spearman's rank correlation of 0.908 vs. 0.150, estimated difference = 0.758 [0.494, 1.021]) and a per-judgment pairwise win-rate metric (0.669 vs. 0.542, estimated difference = 0.127 [0.067, 0.186]), while requiring less than half the annotation time. The patterns hold for human annotators and LLM autograders. Beyond this initial comparison, the paired structure of the dataset supports a broader research agenda on how expert judgment should be elicited, aggregated, and used as supervision in domains without verifiable ground truth.

We formalize and enable the task of open tree decomposition, which segments an image into hierarchical trees of visual components with unconstrained granularity and flexibility. Specifically, we provide the foundation benchmark for this new paradigm with the following three key contributions. First, we overcome the prohibitively high cognitive and physical bottlenecks of manual annotation by developing a fully automated generation pipeline that synergizes the semantic reasoning of Large Vision-Language Models (LVLMs) with the precise geometric grounding of SAM 3. Second, leveraging this pipeline, we construct COCOTree, a massive-scale benchmark featuring over 21K images and 1.8M structural nodes. By embracing an open-vocabulary space of over 3.5K unique labels, it successfully captures the long-tail distribution of complex physical assemblies. Notably, rigorous human evaluation confirms our generated annotations demonstrate strong alignment with human structural judgment. Third, we establish a standardized evaluation protocol by proposing the Open Tree Quality (OTQ) metric, which jointly assesses mask precision, label accuracy, and structural consistency. We release our dataset and benchmark code at https://github.com/melonkick3090/COCOTree.

Presupposition projection in conditionals is central to theories of meaning and pragmatics, yet it remains largely unevaluated in large language models. We address this gap through a parallel behavioral study comparing human judgments and LLM predictions on a normed dataset of conditional sentences that controls the relation between the antecedent and the projected presupposition. We collect likelihood ratings from 120 participants and four LLMs under matched contextual conditions. Results show that humans integrate probabilistic and pragmatic cues in their judgment, whereas LLMs show variable alignment with human patterns. Using a linguistically motivated checklist within an LLM-as-a-Judge framework, we further evaluate model reasoning. We observe models that best match human ratings often lack coherent pragmatic reasoning, while models with stronger reasoning produce less human-like judgments. These findings suggest that LLMs' performance on such tasks may result from surface pattern matching rather than pragmatic competence. Our findings highlight the importance of benchmarks grounded in linguistic theory for comparing humans and models.

Large language models (LLMs) are increasingly used in the mental health domain, yet it remains unclear how well they capture related biomedical knowledge and how reliably they apply it to clinically salient structured judgments. Here, we present a knowledge-graph (KG)-grounded benchmark for assessing LLMs on mental-health entity recognition, relation judgment, and two-hop reasoning. The benchmark is derived from PrimeKG and comprises nine task families with KG-supported answers and controlled negative options. Experiments across 15 closed- and open-source LLMs reveal a persistent recognition-to-judgment gap: leading models achieve near-ceiling performance on entity typing and on the small relation-typing subset, yet they still struggle with relation prediction and two-hop reasoning. Additionally, short KG-derived snippets benefit some models but degrade performance for others. Moreover, output-format reliability can substantially influence measured performance under constrained multiple-choice settings, highlighting the critical role of response validity in benchmark-based evaluation. MHGraphBench should therefore be interpreted as evaluating agreement with a curated mental-health slice of PrimeKG under a constrained multiple-choice interface, rather than as a direct assessment of real-world clinical safety.

Humans naturally communicate through abstract concepts like "mood". However, current image editing benchmarks focus primarily on explicit, literal commands, leaving abstract instructions largely underexplored. In this work, we first formalize the definition and taxonomy of abstract image editing. To measure instruction-following in this challenging domain, we introduce Entity-Rubrics, a framework that breaks down abstract edits into individual, entity-level assessments and achieves strong correlation with human judgment. Alongside this framework, we contribute AbstractEdit, the first benchmark dedicated to abstract image editing across diverse real-world scenes. Evaluating 11 leading models on this dataset reveals a fundamental challenge: standard architectures struggle to balance intent and preservation, commonly defaulting to under-editing or over-editing. Our analysis demonstrates that driving meaningful improvements relies heavily on integrating advanced LLM text encoders and iterative thinking. Looking forward, our entity-based paradigm can generalize beyond assessment to serve as a reward model, enable models to correctly interpret abstract communication, or highlight specific failures in test-time critique loops. Ultimately, we hope this work serves as a stepping stone toward seamless multimodal interaction, closing the gap between rigid machine execution and the natural, open-ended way humans communicate.

In LLM Reinforcement Fine-Tuning (RFT), curriculum learning drives both efficiency and performance. Yet, current methods externalize curriculum judgment via handcrafted heuristics or auxiliary models, risking misalignment with the policy's training dynamics. In this paper, we introduce METIS (METacognitive Internalized Self-judgment), a novel framework that internalizes curriculum judgment as a native capability. Leveraging a critical observation that within-prompt reward variance effectively gauges prompt informativeness, METIS predicts this metric based on recent training outcomes as lightweight in-context learning examples. This intrinsic self-judgment then dynamically dictates the training allocation. Moreover, METIS closes the loop between judgment and optimization by jointly optimizing the standard RFT rewards and a self-judgment reward. This allows the policy to learn what to learn next, as a form of metacognition. Across extensive discrete and continuous RFT benchmarks from mathematical reasoning, code generation, to agentic function-calling, METIS consistently delivers superior performance while accelerating convergence by up to 67%. By bypassing handcrafted heuristics and auxiliary models, our work establishes a simple, closed-loop, and highly efficient curriculum internalization paradigm for LLM reinforcement fine-tuning.

Multiple-choice reasoning benchmarks face dual challenges: rapid saturation from advancing models and data contamination that undermines static evaluations. Ad-hoc hardening methods (paraphrasing, perturbation) attempt to increase difficulty but sacrifice logical validity for surface complexity, falling short to challenge advanced reasoning models. We present LogiHard, a formal framework that deterministically transforms 0-order selection into 2-order logical judgment, which significantly increases the thinking overhead and reasoning steps. The framework integrates Item Response Theory (IRT) for computerized adaptive testing (CAT), enabling precise difficulty control with fewer questions than static benchmarks. We instantiate LogiHard-2k, a logical reasoning dataset constructed by cognitively ranking high-stakes examination questions via 9-dimensional analysis of model thinking traces, followed by combinatorial transformation of high-difficulty items. Evaluation across twelve state-of-the-art models reveals an accuracy degradation ranging from 31% to 56% on combinatorially hardened questions. LLMs suffer from the multi-select failure and early exit bias, which are not shared by human testees. Zero-shot transfer to MMLU demonstrates 47% accuracy degradation (89.84% to 42.86%), confirming applicability across domains with provable validity preservation. The consistent aggregate degeneration is domain-agnostic and stems not from knowledge deficits but from a combinatorial reasoning gap, reflecting a training-induced completeness-verification deficit.

Aligning large language models with expert judgment is especially difficult in subjective evaluation tasks, where experts may disagree, rely on tacit criteria, and change their judgments over time. In this paper, we study expert alignment as a way to understand this difficulty. Using expert evaluations and follow-up questionnaires, we examine how different forms of expert information affect alignment and what this reveals about subjective judgment. Our findings show four consistent patterns. First, alignment difficulty varies substantially across experts, suggesting that expert evaluation styles differ widely in their distance from a model's prior behavior. Second, explicit criteria and reasoning do not always improve alignment, indicating that expert judgment is not fully captured by verbalized rules. Third, editing is sensitive to both the number and the identity of examples, with small numbers of edits providing useful but unstable gains. Fourth, alignment difficulty differs across evaluation dimensions: dimensions grounded more directly in proposal content are easier to align, while dimensions requiring external knowledge or value-based judgment remain harder. Taken together, these results suggest that expert alignment is difficult not only because of model limitations, but also because subjective evaluation is inherently heterogeneous, partly tacit, dimension-dependent, and temporally unstable.

Each major technological revolution inverts a particular scarcity and rebuilds institutions around the shift. The near-consensus diagnosis of the AI revolution holds that AI collapses the cost of prediction while judgment remains scarce. This Opinion argues the inversion has now flipped: competent-looking judgment (selecting, ranking, attributing, certifying) is produced at scale and at marginal cost approaching zero, and four complements become scarce: verified signal, legitimacy, authentic provenance, and integration capacity (the community's tolerance for delegated cognition). Because judgment is the substance of institutions, the institutions built to manufacture legitimate judgment (courts, journals, licensing bodies, legislatures) now compete with the technology for the same functional role. The piece traces the pattern across scientific institutions, professional licensing, intellectual property, democratic legitimacy, and foundation-model concentration, and closes with a three-move agenda: reframe AI policy as institutional redesign, build provenance and verification as commons, and develop the formal apparatus for institutional composition under strategic agents.

Human moral judgment is context-dependent and modulated by interpersonal relationships. As large language models (LLMs) increasingly function as decision-support systems, determining whether they encode these social nuances is critical. We characterize machine behavior using the Whistleblower's Dilemma by varying two experimental dimensions: crime severity and relational closeness. Our study evaluates three distinct perspectives: (1) moral rightness (prescriptive norms), (2) predicted human behavior (descriptive social expectations), and (3) autonomous model decision-making. By analyzing the reasoning processes, we identify a clear cross-perspective divergence: while moral rightness remains consistently fairness-oriented, predicted human behavior shifts significantly toward loyalty as relational closeness increases. Crucially, model decisions align with moral rightness judgments rather than their own behavioral predictions. This inconsistency suggests that LLM decision-making prioritizes rigid, prescriptive rules over the social sensitivity present in their internal world-modeling, which poses a gap that may lead to significant misalignments in real-world deployments.

Moral judgements form the foundation of human social behavior and societal systems. While Artificial Intelligence chatbots increasingly serve as personal advisors, their influence on moral judgments remains largely unexplored. Here, we examined whether directive AI conversations shift moral evaluations using a within-subject naturalistic paradigm. Fifty-three participants rated moral scenarios, then discussed four with a chatbot prompted to shift moral judgments and four with a control agent. The brief conversations induced significant directional shifts in moral judgments, accepting stricter standards as well as advocating greater leniency (ps < 0.05; Cohen's d = 0.735-1.576), with increasing strengths of this effect during a two-week follow-up (Cohen's d = 1.038-2.069). Critically, the control condition produced no changes, and the effects did not extend to punishment while participants remained unaware of the persuasive intent, and both agents were rated equally likable and convincing, suggesting a vulnerability to undetected and lasting manipulation of foundational moral values.

Debates about artificial intelligence (AI) in education often portray teaching as a modular and procedural job that can increasingly be automated or delegated to technology. This brief communication paper argues that such claims depend on treating teaching as more separable than it is in practice. Drawing on recent literature and empirical studies of large language models and retrieval-augmented generation systems, I argue that although AI can support some bounded functions, instructional work remains difficult to automate in meaningful ways because it is inherently interpretive, relational, and grounded in professional judgment. More fundamentally, teaching and learning are shaped by human cognition, behavior, motivation, and social interaction in ways that cannot be fully specified, predicted, or exhaustively modeled. Tasks that may appear separable in principle derive their instructional value in practice from ongoing contextual interpretation across learners, situations, and relationships. As long as educational practice relies on emergent understanding of human cognition and learning, teaching remains a form of professional work that resists automation. AI may improve access to information and support selected instructional activities, but it does not remove the need for human judgment and relational accountability that effective teaching requires.