LLM Reliability

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

78 papers in the last four weeks, up 105% on the four weeks before. 0.8% of all new papers.

Jul 13Week of Sep 28

Latest papers 507

Sep 16, 2026cs.HC

GYROval: A Robust Benchmark for Cultural Value Orientation in Large Language Models

We present a robust benchmark for measuring cultural value orientation in large language models on the two Inglehart-Welzel axes over several domains and roles (hence GYROval - Gridded Yielding of Robust value Orientation), together with the results of administering it to twenty models. Items are binary contrastive scenarios in the sense introduced by CDEval: both options are legitimate courses of action, neither is correct, there is no answer key, and a model's score on an axis is the proportion of its responses falling on the counted pole. Eleven of the twenty models were additionally administered a paired Russian translation of the identical items and a second sampling temperature. The instrument is publicly released in both languages. Stability was assessed by treating the vignette as the unit of analysis, ranking the models within the levels of each perturbation factor, and summarising the agreement between levels by tie-corrected Kendall's \emph{W} against an empirical permutation null.

Alexander Didenko, Anna Shabanova, Vladislav Zapylikhin +2

Artificial Intelligence Laboratory, SKOLKOVO School of Management, Moscow · Artificial Intelligence Laboratory, University of Tyumen · Institute of Business Studies, Russian Presidential Academy of National Economy and Public Administration, Moscow

LLM Evaluation Cross-Cultural Language Model Evaluation LLM Reliability Cultural Bias in Language Models

Sep 16, 2026cs.SE

An Empirical Evaluation of Cost-Efficient Large Language Models on Algorithmic Programming Tasks

This study empirically evaluates whether cost-efficient Large Language Models (LLMs) can be trusted to generate enterprise code to a written specification. Three models (Gemini Flash 3, GPT-5.4 mini and Claude Haiku 4.5) were asked to solve 992 algorithmic problems as Java Spring Boot service methods conforming to a mandated signature and data-transfer-object specification, crossing four model and agentic coding tool combinations with two prompt variants to yield eight configurations, with iteration forbidden and hardcoded answers explicitly prohibited. Eight problem statements were withheld to probe how models respond to missing input. The 7,593 resulting methods were classified by an eight-class outcome taxonomy describing what each does about producing an answer, then deployed and executed, giving 7,936 measured requests joined to that classification. Structural conformance approached ceiling, yet 38.4% of methods do not compute the value they returned and only 12.9% of returned answers were correct. Conditioning on outcome class shows that response reliability and correctness are inversely related, whereas genuinely computing methods answered least often and were correct 19.3%. Limitations include single generation runs per configuration, partial harness coverage, single-pass timing, syntactic classification, and probable corpus contamination.

Chandimal Adikari, Nandika Herath

Faculty of Engineering and Information Sciences University of Wollongong Wollongong, Australia · Faculty of Engineering, Computing and Science Western Sydney University Parramatta, Australia

Code Generation LLM Reliability Code Generation Evaluation Code Language Models

Sep 15, 2026cs.LG

The Missing "I Don't Know": Why Three Reasoning-Reliability Findings Converge on Calibrated Abstention

Three recent results describe what look like unrelated LLM reliability problems. Yin et al. (2026) show reasoning RL collapses tool-reliability representations. Suleymanov et al. (2026) show that under safety-constrained generation, large models rewrite flagged spans while small models truncate. Bastounis et al. (2024) prove any consistent-reasoning system without an implicit "I don't know" function must hallucinate infinitely often on broad problem classes. We argue these findings converge on a single intervention: calibrated abstention is what each independently identifies as the missing capability, even though the unavailability they document, a capability gap, a policy gap, and a recursion-theoretic gap, has a different source in each case. Honesty post-training has narrowed the gap in deployed models, but principled closure of the class Bastounis identifies requires a calibrated abstention function whose training signal at the leaderboard level is absent: dominant benchmarks assign zero reward to decline, so the leaderboard gradient that would select for the function does not exist. We propose four changes to evaluation: triple-scoring, abstention-rate reporting, capability-stratified evaluation, and mandatory calibration metrics. Benchmark reform is necessary, not sufficient, for closing the gap the theorem identifies.

Srijith Ravikumar

Amazon.com LLC

Language Model Safety Evaluation Language Model Calibration LLM Reliability

Sep 15, 2026cs.LG

Easy to Catch a Liar, Hard to Clear an Honest One: Language Models Diagnosing a Corrupted Reward Channel from a Verified Record

An agent that learns from rewards has to trust whatever reports those rewards. When the reports suddenly change, either the world changed or the reporter broke. From the reports alone these are indistinguishable, and reinforcement learning theory shows that no amount of further experience separates them. The prescribed escape is richer data about the reporter itself. We ask whether a frozen language model, handed exactly that data, uses it. We build a two-option game in which a payout swap and a lying reporter produce byte-identical histories. Then we add one verified record: an independent check of one round's real result, printed beside what the reporter said about that round. That single line settles the case. We ask three large models, from two families, to answer one question with one letter. Is the reporter honest or lying? They catch a lying reporter almost perfectly. At the 70B class that holds in every condition we tried; the 32B model slips in one wording. They clear an honest reporter far less often, and how often depends on things that should not matter. Averaged over rounds, letters, and wordings, a 72B model calls an honest reporter a liar 38% of the time when nothing has changed at all, and 58% of the time when the payouts moved. A 70B model from a second family calls an honest reporter a liar 26% and 48% of the time. The failure is not one of reading, because in the situation where nothing changed the same models score 0.96 to 1.00 with the answer printed in the prompt. Which surface feature drives it differs by family. For the Qwen models it is which round the record names, and for Llama it is which letter stands for "honest." Adding the record to a prompt that already states the answer makes Llama less likely to give that answer. We had registered a prediction for that 58% before the run: 35%. The failure is larger than we expected.

Arman Nik Khah

The University of Texas at Dallas

LLM Auditing Deception in Language Models LLM Reliability

Sep 15, 2026cs.CL

An Empirical Study of Counterfactual Self-Explanations in LLMs

Large language models can easily generate explanations for their own outputs, but such self-explanations are not necessarily faithful to the model's behavior. We study this issue through counterfactual self-explanations, where a model minimally edits an input so that its own prediction changes. Across sentiment analysis and natural language inference, we evaluate ten instruction-tuned models from the LLaMA-3 and Qwen-2.5 families, measuring faithfulness, minimality, and alignment with human-annotated rationales. Our results show that model scale is the strongest determinant of explanation quality: larger models are substantially more likely to generate counterfactuals that flip their own predictions and target decision-relevant evidence. In contrast, the rationale-guided condition produces edit-minimal counterfactuals that are also more human-aligned. However, it does not consistently improve faithfulness. Overall, counterfactual self-explanations can provide useful behavioral evidence about model decisions, but their reliability depends strongly on model capacity and should be empirically validated rather than assumed.

Giannis Kalyvas, Giorgos Filandrianos, Orfeas Menis Mastromichalakis +2

National Technical University of Athens, Athens, Greece · Instituto de Telecomunicações, Lisbon, Portugal

Counterfactual Explanations Faithfulness of Language Model Explanations LLM Interpretability Counterfactual Reasoning in Language Models LLM Reliability

Sep 14, 2026cs.CL

When the Wrong Key Wins: Understanding and Detecting Hallucinations in LLMs

Large language models can hallucinate even when the knowledge required for a correct answer is already available. We study this failure through a latent-key view of inference, where answer selection depends on competition among associations acquired during pretraining. We show that model predictions can be highly sensitive to individual query keywords, that these influential keywords exhibit entity-specific binding, and that their effects are systematically shaped by pretraining frequency. Multiple bindings can also compete and exhibit higher-order interactions within the same query. Based on this mechanism, we introduce a two-stage keyword-perturbation method for hallucination detection. By removing influential keywords and measuring how the model reorganizes its prediction, the method distinguishes errors caused by misleading key associations from correct decisions supported by diagnostic evidence. Across multiple models and benchmarks, perturbation provides a strong and transferable detection signal, reaching

0.910

AUROC on probe-known ScientistQA. Finally, we extend the same probabilistic framework to four hallucination regimes: knowledge deficit, wrong knowledge, context distraction, and unstable inference. Their operational distributions across benchmarks provide diagnostic context for why different detector families succeed in different settings.

Xuhan Tong, Haoyue Bai, Dawei Zhou +2

University of Wisconsin–Madison

Language Model Error Detection Hallucination in Language Models LLM Reliability LLM Hallucination Detection Language Model Probing

Sep 14, 2026cs.SE

PRISMA-LLM: An Empirical Reporting Framework for AI-Assisted Systematic Reviews

Large language models (LLMs) and AI-enabled software increasingly participate in systematic-review decisions, yet the information needed to audit these workflows is reported inconsistently. We analyze SciLitBench, a corpus of 888 review-automation papers with 14,726 annotations, to characterize changes in methods, review-stage use, evaluation and reported limitations. Automation has shifted toward LLM- and software-facing workflows, including stages that can alter the evidence base. Since 2023, 38.0% of software/product papers reported no evaluation, compared with 9.3% of LLM papers. Reporting coverage increased with LLM workflow complexity, yet 52% of positive-only LLM evaluations still reported an unmet reliability or performance requirement. From these patterns, we introduce PRISMA-LLM, an empirically grounded framework separating implementation disclosure from consequence-sensitive evaluation and limitation reporting.

Miguel Zabaleta, Baihan Lin

Department of AI and Human Health, Icahn School of Medicine at Mount Sinai, New York, NY, USA · Department of Psychiatry, Icahn School of Medicine at Mount Sinai, New York, NY, USA · Department of Neuroscience, Icahn School of Medicine at Mount Sinai, New York, NY, USA

LLM Auditing AI-Assisted Scientific Research LLM Reliability Automated Evaluation

Sep 14, 2026cs.LG

Can We Trust LLM Judges: A Study of Capability-Dependent Biases and Multi-Judge Ensemble for Bias Calibration

LLMs are increasingly used as automated judges for model training and evaluation, yet individual judges exhibit systematic biases that undermine reliability. Much of prior work has studied biases in pairwise LLM-as-a-judge settings; in this paper, we focus on absolute scoring tasks, which mirror more realistic use cases. Across four benchmarks and six models (36 judge-examinee pairs), we show that a model's task accuracy strongly predicts its judging accuracy (Pearson

r \geq 0.90

on most models) and inversely predicts its directional bias (

r \leq -0.83

), but that accuracy alone does not ensure fair evaluation: more capable examinee models consistently receive more lenient judgments from all judges (

r \geq 0.83

). To address this, we propose calibrated weighted majority voting (WMV), an ensemble evaluation method that aggregates multiple LLM judges weighted by online estimates of their false-positive and false-negative rates. We introduce a disagreement-based estimator that derives these error rates purely from inter-judge agreement patterns, requiring no ground-truth labels or task metadata. In a simulated experiment with shifting task distributions, our label-free WMV tracks an oracle with perfect error-rate knowledge to within 0.5 percentage points on average, outperforming both individual judges and unweighted majority voting. These results demonstrate that principled multi-judge calibration can simultaneously improve accuracy and correct for systematic leniency without requiring labeled data, offering a scalable path to reliable automated evaluation as model capabilities increase.

Gemma Zhang, Prachi Badarayani, Asmi Kumar +2

Microsoft · Massachusetts Institute of Technology

LLM Evaluation LLM-as-a-Judge Language Model Calibration LLM Reliability Language Model Bias Evaluation Bias in LLM-as-a-Judge+1

Sep 14, 2026cs.AI

Competence-Gated Pooling of Language Models and Priors for Event Forecasting

In hybrid forecasting, a language model is often one of several available signals. A system may already have a market, crowd, or statistical forecast and must decide whether the model adds useful information or should be ignored. The relevant target is therefore not standalone model accuracy, but relative competence, defined as the model's marginal value beyond the available external forecast. Under Brier loss, we characterize when model disagreement can improve an external forecast and derive the gain from using domain-specific rather than global pooling weights. We then introduce a competence gate that estimates domain-level source weights from resolved outcomes, shrinks uncertain estimates toward a global weight, and recalibrates the pooled forecast. Across 2,357 resolved binary questions and five language models, the gate improves the main external baseline from 0.0771 to 0.0732 Brier and significantly outperforms global forecast combinations. The gain remains significant under leakage controls and against a leakage-safe time-series prior on the pooled structured set, with separate evidence on FRED. In contrast, the gate gives no significant improvement on the official ForecastBench market subset, where it largely defers to the market. Across four Qwen models, verbal confidence does not reliably identify when the model outperforms the external forecast, while outcome-estimated competence supports better abstention decisions. These results provide a practical approach for selective model use based on measured marginal value.

Aditi Tiwari, Aashrith Bandaru, Heng Ji

University of Illinois Urbana-Champaign Urbana, Illinois, USA

Event Time Prediction Selective Prediction Probabilistic Forecasting LLM Reliability

Sep 14, 2026cs.AI

Language Is an Insufficient Substrate for Quantitative Reasoning, and Consequential Domains Need Large Quantitative Models

The prevailing assumption in applied machine learning is that progress on consequential quantitative decisions such as pricing risk, allocating capital, triaging patients, or containing a network intrusion will follow from progress in large language models (LLMs). A language model is trained on a representation of the world that was produced by human description; description is a lossy encoding of the quantitative record, and the loss is irreversible: no downstream model, at any scale, can recover from a description what the description did not encode. We formalize this as a property of the representation on which a model is trained rather than of the model capacity, and we identify three further properties that consequential settings demand of a model and that a language substrate cannot supply by construction: reproducibility, lineage from every output back to the source records that produced. it, and calibrated uncertainty. We argue that these properties define a distinct model class, which we call the Large Quantitative Model (LQM).

Reuben Vandeventer, David Imrem, David J. Wild

Duo Dimensio LLC · Luddy School of Informatics, Computing and Engineering, Indiana University

Numerical Reasoning in Language Models LLM Reliability

Sep 14, 2026cs.AI

Can LLMs in Draft-Verify-Revise Pipelines Resolve Deictic Ambiguity?

Draft-verify-revise is a common LLM orchestration pattern for scaling inference-time compute. One LLM drafts, a second critiques the draft and provides feedback, and a third uses that feedback to revise the draft into the final output. As context cascades between stages, LLMs at different stages can resolve a context-dependent expression such as "previous" differently. When that happens, the expression undergoes a deictic shift, a change in what it refers to. This phenomenon was studied with a synthetic dataset of 10 base examples, each rendered in three conditions. Holding the shared components constant, the conditions varied whether the draft stage LLM (the assistant) or the verify stage LLM (the grader) resolved the expression correctly, and how much independent reasoning the revise stage LLM (the meta-evaluator) needed to determine which reading was correct. Six models from three providers were tested across 21 reasoning effort configurations using e-values for sequential testing, in a primary experiment and an ablation experiment that removed error classification labels from the grader's feedback. A separate LLM analyzed the meta-evaluator's stated rationale for each wrong verdict. Balanced accuracy (the unweighted mean of sensitivity and specificity) ranged from 0.156, below chance, to near-perfect. GPT-5.2 rose from 0.156 without reasoning to 0.942 at its highest reasoning effort level, while Gemini 3 Pro stayed above 0.94 at every level. Gemini 3 Pro at low reasoning effort outscored GPT-5.2 at xhigh reasoning effort for roughly 5% of the cost per trial. When the meta-evaluator erred, it tended to rely on surface cues rather than operational reasoning. Context engineers implementing draft-verify-revise pipelines should be wary of deictic shifts and make the intended referent explicit at each stage.

Obinna I. Ekekezie

Cambridge Health Alliance, Cambridge, MA, United States of America. · Harvard Medical School, Boston, MA, United States of America.

Coreference Resolution LLM Answer Verification LLM Reliability LLM Reasoning

Sep 14, 2026cs.LG

SAGE-Loop: Reliable Closed-Loop LLM-Driven AutoML with Trial-and-Correction and Adaptive Ensembling

Automated machine learning (AutoML) is reshaping data-driven science and industrial practice, and as large language models are introduced into AutoML, pipeline reliability becomes as important as automation efficiency. However, existing AutoML still struggles to realize instant feedback and adaptive optimization during execution, so once a run drifts into a suboptimal or failed state, it lacks a process-level correction mechanism. The fundamental pathology lies in its one-way pipeline: intermediate failures are typically terminated or bypassed, while fixed paradigms often strengthen model generation but leave ensemble decisions static, weakening both execution reliability and the controlled use of structural diversity. This indicates that LLM-driven AutoML needs a closed-loop ability for trial-correction-improvement together with evidence-based use of model diversity. To this end, we propose SAGE-Loop, a reliable closed-loop, self-adaptive, LLM-driven AutoML framework that performs multi-round generation and validation for trial-and-repair, and adaptively selects ensemble strategies in both supervised and unsupervised tasks, thereby unifying how to generate with how to use models. Across 20 public datasets, SAGE-Loop consistently improves performance and stability on classification, regression, and clustering tasks. Additional results further show its ability to recover from execution failures and maintain robust pipeline behavior.

Junquan Gu, Shibo Cui, Xiangfeng Luo +1

LLM Self-Correction Ensemble Learning Large Language Model-Guided Optimization LLM Reliability Automated Machine Learning

Sep 14, 2026cs.CL

Biomedical Reference Generation Remains Unreliable across 26 Large Language Models

Background. Large language models are increasingly used to help write biomedical text but may fabricate references to nonexistent work. How often large language models do so is not well characterized. Methods. We prompted 26 language models from eight developers (2023 to 2026) to supply a missing reference for each of 69 biomedical passages across ten domains. References were classified as verifiable (real paper with a resolving identifier), partial matches (real paper without a resolving identifier), fabricated (no matching indexed paper), or declined (the model refused to supply a reference). A reference was considered correct in every evaluated bibliographic field only when it was verifiable and its journal, year, and listed authors matched those of the cited paper. Results. Fabrication ranged from 10.2% (Claude Opus 4.8, which declined 52.1% of prompts) to 98.4% (Ministral 3B, which produced no verifiable reference). Claude Opus 4.6 and Claude Sonnet 4.5 produced similar proportions of verifiable references (77.6% and 76.6%) but named authors correctly in 78.7% and 28.7% of author-evaluable verifiable references, respectively, and were correct in every evaluated field in 54.6% and 19.9% of responses. GPT-5.5 was correct in every field in 48.1%. Across all models, 55.4% of responses were fabricated and 14.9% were correct in every field. Among the five tested models first released in 2026, the corresponding proportions were 35.3% and 31.8%, respectively. Conclusions. Fabrication remained common, and no model was correct in every evaluated bibliographic field in more than 54.6% of responses. Models that identify real papers may still misstate their metadata, so references produced with model assistance require verification before use.

Maxim Topaz, Zhihong Zhang, Nir Roguin +3

School of Nursing, Columbia University, New York, NY, USA · Data Science Institute, Columbia University, New York, NY, USA · VNS Health, New York, NY, USA +4

LLM Evaluation Hallucination in Language Models LLM Reliability Text Generation

Sep 12, 2026cs.AI

Towards a Deterministic Math Solver for Clinical Language Models

Large language models are unreliable at arithmetic, which is a problem for clinical calculators where a single numerical error changes the recommendation. The standard response is to hardcode each calculator as a validated function, one at a time. We test an alternative: the model does not calculate. Instead, it writes case-specific Python that a restricted local executor runs as a deterministic solver, and the model's task reduces to deciding how to use it. We evaluate this Program-Solve interface on MedCalc-Bench Verified (1,100 cases, 55 calculators) against direct model arithmetic and a hand-written 22-calculator library, using Qwen2.5-7B and Qwen2.5-32B-AWQ, after auditing the benchmark's formulas against current clinical guidelines and flagging 16 of 55 with version, use or coefficient concerns. With formulas and gold variables supplied and both routes reading the whole note, handing off to the solver is not a reliable advantage at 7B (75.31% against 72.02%, a paired +3.29 points with a 95% calculator-cluster interval of [-3.49, 10.38]) but is one at 32B (90.53% against 83.47%, +7.05 [0.47, 14.60], clear of zero). The hand-written library is exact on its 440 supported cases but abstains elsewhere (40.0% overall). Adding an executor thus helps some open-weight models more than others even under matched formula, variable and note access, and is not a substitute for verified formulas or reliable variable extraction either way.

Felipe Ocampo Osorio, Sebastián Andrés Cajas Ordoñez, Maximin Lange +5

MIT Critical Data · UNC Chapel-Hil · University of Pavia +1

Numerical Reasoning in Language Models LLM Reliability LLM Tool Use Clinical Language Model Evaluation LLM Code Generation

Sep 12, 2026cs.AI

Beyond Confidence: Stability-Aware Test-Time Adaptation for LLM Reasoning

Test-time adaptation has emerged as a lightweight alternative to costly post-training for improving the reasoning capabilities of Large Language Models (LLMs) on downstream tasks. Predictive entropy provides a model-derived signal for such adaptation, guiding models toward higher-confidence reasoning states without external verifiers or reward models. However, higher confidence does not necessarily imply correctness, as LLMs may remain highly confident along incorrect reasoning trajectories. We observe that high-confidence reasoning is more likely to be correct when confidence remains stable under local perturbations. Based on this observation, we propose Test-Time Adaptation via Stability-Aware Confidence Optimization (TASCO), a framework that incorporates local stability into confidence-based test-time adaptation while keeping the LLM frozen. TASCO operationalizes local stability by optimizing a lightweight task-level prefix under two alternative perturbation strategies: Random Perturbation promotes distributional stability across trajectories induced by nearby perturbed prefixes, whereas Sharpness-Aware Perturbation targets worst-case local sensitivity. Experiments demonstrate that TASCO improves reasoning accuracy and token efficiency across diverse LLMs and reasoning benchmarks, while behavioral analyses show that it maintains stable confidence under local perturbations without prematurely concentrating the model's predictive distribution.

Bincheng Gu, Min Gao, Zongwei Wang +3

Key Laboratory of Dependable Service Computing in Cyber Physical Society, Chongqing University, China · King’s College London, London, UK · Griffith University, Brisbane, Australia

Test-Time Adaptation LLM Reliability LLM Reasoning

Sep 11, 2026cs.CL

Can LLMs Normalize Databases? A Benchmark and Multi-Agent Framework for Schema Normalization

Large Language Models (LLMs) are increasingly used to generate structured outputs, but their reliability remains unclear when those outputs must satisfy database-level constraints. We study this issue through database normalization, involving reasoning about functional dependencies, lossless join decompositions, and inter-table constraints. We introduce a Database Normalization Benchmark (DNBENCH), comprising 3,275 samples for evaluating LLM-driven database normalization from 1NF to BCNF. DNBENCH uses a three-axis protocol to measure semantic equivalence, structural accuracy, and logical validity. Across Single, Complex, and Real World levels, DNBENCH uncovers recurring failures in dependency inference, schema decomposition, and inter-table constraint reconstruction. We further propose Multi-Agent Reasoning for Schemas (MARS), which separates evidence extraction, violation diagnosis, and decomposition planning from schema generation and verification. MARS improves the DNB-SCORE by 82.0% over the single-prompt baseline. All artifacts will be released upon acceptance.

Dong-Jae Koh, Huisu Kim, SeongHwan Yoon +4

School of Computer Science and Engineering, Kyungpook National University, South Korea

Multi-Agent LLM Systems LLM Reliability Relational Databases

Sep 11, 2026cs.LG

Legible Failures: Detecting and Repairing In-Context Binding Errors

A wrong answer does not show whether the model lacked the needed information or held it and failed to use it. On an entity-obligation binding task, a language model can emit an incorrect prompt-supplied binding while a linear probe can recover the correct one from its frozen hidden state. We measure how often this occurs across 16 public checkpoints, each evaluated with three seeds. We fit a probe on a training fold, select its layer on a validation fold, and report results on a disjoint test fold. On the trials each model gets wrong, probe accuracy exceeds the strict present-obligation baseline, 1/K = 0.125, by +0.196 (95% CI [+0.101, +0.296], bootstrapped over models). A query-entity counterfactual rules out token presence and recency. A score built from the sign of probe-output disagreement improves failure detection over the model's own confidence by +0.079 AUROC (95% CI [+0.036, +0.126]). Raw probe confidence gives no measurable improvement over model confidence. Steering the residual stream toward the probe-decoded binding, with no gold label, raises accuracy on all eight models tested by a mean of +0.168 (95% CI [+0.066, +0.280]). Where recent studies report that probe-detected errors are resistant to interventions, we find that in-context binding is a setting in which probes are actionable.

Manas Venkata Sai Ravulapalli, Samrath Singh Chadha, Abhinav M. Hari

Efficient Computation Inc.

Language Model Error Detection LLM Reliability In-Context Learning Language Model Probing

Sep 11, 2026cs.DL

INDRA: A New AI Tool for Exploring Tobacco, Fossil Fuel, and Chemical Industry Archives

Five decades of litigation have disgorged hundreds of millions of pages of formerly secret business records from the tobacco industry, along with documents from the makers of drugs, chemicals, food, firearms, and fossil fuels. Yet these archives have been effectively inaccessible to general-purpose large language models (LLMs) because they have never been compiled into an LLM-readable corpus. Chatbots may be familiar with some of the materials contained in such archives but, with no direct access to the documents, they are vulnerable to hallucination and other defects. Here we introduce INDRA, a research platform designed to remedy such failures by embedding the conventions of archival historiography into a system-level protocol governing every output. The platform federates UCSF's Industry Documents Library, Columbia and CUNY's ToxicDocs, Stanford's SRITA, and other heretofore siloed collections, and provides three interlinked safeguards: (1) a closed evidentiary sandbox confines the model to a user-selected corpus, blocking retrieval from external sources that could introduce bias; (2) real-time provenance tagging marks the boundary between archival evidence and parametric inference; and (3) a system-level protocol enforced by deterministic scripts guides the structure of every output. Together these safeguards prevent the model from conflating "the documents say X" with "I think X" or "I learned X from prior training." The result is an LLM-powered research partner enabling massive multi-archival investigations, a tool whose outputs are designed to be checked rather than trusted, and whose architecture makes the conditions of knowledge production visible and auditable. Three case studies demonstrate the method's analytical value and limitations, including what we call the Heraclitus effect, the steppingstone dilemma, and the gullibility (or mafia) problem.

Daniel Akselrad, Robert N. Proctor

Department of Epidemiology & Population Health, Stanford University, Stanford, CA, USA · Department of History, Stanford University, Stanford, CA, USA

Retrieval-Augmented Generation LLM Reliability

Sep 9, 2026cs.SE

If It's Not Buggy, Don't Fix It: On the Dynamics of Iterative Bug-fixing with LLMs

Large language models (LLMs) have become ubiquitous in software development, with LLM-based automated program repair tools increasingly used during code review. In this report, we explore the iterative blind use of LLMs as bug-fixers. Across multiple models and repair environments, we find that LLMs consistently claim to detect bugs in entirely bug-free programs while the rate of repair of buggy programs is less than that of the damage to correct programs. We also explore the long-term dynamics of this iterative process, and find that this frequently reaches a pseudo-bug-fixing cycle where the same changes are added and removed again ad infinitum. Lastly, via mechanistic probing, we unveil the existence of a steering vector which controls the editing propensity, suggesting that LLMs have an internal representation of ``buggy code", and that this representation is what is falsely activated to induce pseudo-bug fixing. These results provide insight towards the dynamics of fully autonomous bug-fixing systems, as well as stopping conditions under ambiguous goals.

Xietao Wang-Lin, Anton Isopoussu, Louis Mahon

University of Warwick · UnlikelyAI

LLM Self-Correction Automated Program Repair LLM Reliability

Sep 9, 2026cs.CL

ProbPlug: A Plugin Uncertainty Network for Reliable Confidence in LLM Binary Classification

Large language models (LLMs) have achieved strong performance across a broad range of classification settings, yet the reliability of their predictions remains a major obstacle to deployment in high-stakes scenarios. Although confidence estimation for LLMs has been widely studied, confidence calibration for LLM-based classification remains underexplored. We introduce ProbPlug, a lightweight confidence estimation framework for LLM-based binary classification, which predicts whether an output is correct using internal token features extracted from a frozen LLM. ProbPlug employs a self-attention module to aggregate hidden representations and can be integrated into the original inference pipeline without modifying the base model. Experiments across multiple tasks involving both text-based and multimodal large models show that ProbPlug provides more reliable confidence estimates, improves classification performance with negligible additional overhead, and exhibits strong generalization across tasks. These results indicate that ProbPlug serves as a practical solution for confidence estimation in LLM-based classification. Our code is publicly available at Github.

Jianzong Wang, Chuhang Liu, Botao Zhao +6

Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, China · Tsinghua Shenzhen International Graduate School, Shenzhen, China · Hubei University of Technology, Hubei, China

Confidence Estimation in Language Models Language Model Calibration LLM Reliability Classification LLM Uncertainty Estimation

Sep 9, 2026cs.CL

Stable Answers, Unfinished Reasoning: Why Self-Consensus Is Not a Safe Early-Exit Signal

A natural way to cut reasoning-model inference cost is to repeatedly probe a single partial trajectory for its current answer and stop once probes agree -- self-consensus. We ask whether any such rule is both safe and token-saving, and whether one can be selected once and reused. A preregistered sweep of 3,520 consensus rules, replayed on frozen trajectories from two models and three benchmarks, clears none of three acceptance gates fixed in advance; the frontier reproduces on a held-out split and on two unseen models -- while a boundary-confidence control (DEER) swept through the same pipeline clears all three. The reason lies in the signal: agreement establishes that the current answer persists under a fixed probing procedure, not that the reasoning has terminated -- a consensus-termination gap. Stopping on it commits non-terminal answers. At a rule still saving 32% of the tokens, one stop in nine fires on an answer the trajectory itself later abandons, and most of those stops cut off a correction it would otherwise have made. Widening the agreement window does not remove them: the share levels off near 7%, and by then the saving has fallen to 8%. Probe re-wording and a hand-labelled error taxonomy show the agreed answer is often a placeholder the model had not settled on. Used on its own as the stop signal, agreement fails not because it is insufficiently strict, but because it repeatedly measures the wrong object.

Yunxiang Mo, Donghao Zhao, Hejia Geng

HKUST · University of Oxford

Early Stopping LLM Reliability Efficient Language Model Inference Large Reasoning Models

Sep 9, 2026cs.AI

Proof-Carrying Cognition: Closing the Verification Gap with Reality-Settled Reward

Frontier gains in language-model reasoning come from reinforcement learning on reasoning traces and are concentrated in domains with a cheap, sound verifier. We argue the field's binding constraint is the verification gap: no scalable, incorruptible reward for reasoning outside formal domains. We make four contributions. (1) Theory: in a joint-Gaussian model of best-of-N selection, verifier-gold correlation rho is the exact exchange rate between test-time compute and capability, and an unsound verifier pays a polynomial penalty N^(1/rho^2); a margin-free copula form predicts realized soundness of real LLM judges to 4% median error. (2) Demonstration: in program-synthesis testbeds with executable ground truth, including a pre-registered scaled replication, unsound verifiers lose Soundness-under-Pressure as optimization grows (0.94 to 0.32 at N=4096) while a sound verifier improves monotonically; reality-anchored settlement beats a frozen verifier under i.i.d. and adversarial pressure, driving the hacking gap from ~0.27 to ~0; soundness scales log-linearly with settled labels, with on-policy settlement ~10x more label-efficient than random labeling. With real LLM judges and unit-test execution as gold, a weak judge loses soundness under best-of-N (p<0.001), a stronger judge is more robust, and selection alone manufactures +0.53 hacking gaps from honest samples. Under real GRPO training, a frozen reward model traces the full overoptimization curve (executed reward collapses 90%) while the same model refit on a 10% settlement stream preserves 6x the executed reward. (3) Paradigm: proof-carrying cognition, where reasoning steps are typed probabilistic claims priced by a self-built world model trained only on held-out reality and settled by proper scoring rules. (4) Benchmark: we specify Soundness-under-Pressure as the headline metric for a reality-settled reasoning benchmark.

Eshwar Reddy M, Sourav Karmakar

AI Engineer, Testsigma University of San Diego · Senior AI Scientist, Intuit India

Reward Modeling Reward Hacking LLM Reliability Reinforcement Learning with Verifiable Rewards

Sep 8, 2026cs.CL

When Models Defer to Wrong Answers: A Robustness Audit of Source-Attributed Cues in Multiple-Choice QA

Language models often receive a question together with a claim about what another source answered. We audit whether such claims destabilize answers in multiple-choice question answering. For each item, we hold one wrong option fixed across misleading conditions and vary the cue template attached to it. We introduce \emph{neutral-conditioned misleading cue adoption rate} (NC-MCAR), which measures switches to that option only on valid cued trials where the same model first selected the gold answer under a neutral prompt. This is a measure of answer instability, not proof that the model knew the answer or that all deference is irrational. We evaluate four instruction-following models on MMLU-Pro and IndicMMLU-Pro in English, Hindi, Bengali, Tamil, and Telugu. Across 220{,}000 outputs, the expert template yields 41.1% aggregate NC-MCAR, compared with 12.5% for the majority template. These two conditions use the same wrong option and final instruction. Filler accuracy remains well above expert-wrong accuracy, while correct-cue prompts have high valid-response accuracy. The audit documents answer instability relevant to grounding under the tested forced-choice prompts: a bare, unverified source claim can outweigh an answer that was previously consistent with the task evidence.

Manikandan Ravikiran, Siddharth Vohra

Indian Institute of Technology Mandi, India · Carnegie Mellon University Amazon Web Services AI Native Pittsburgh, PA, USA

Multiple-Choice Question Answering LLM Reliability Language Model Auditing

Sep 8, 2026cs.AI

API Benchmark Scores Do Not Reliably Transfer to Chatbot Interfaces

Benchmark scores are a central currency in model releases: they inform purchasing decisions, shape public trust, and influence policy. Yet, a key assumption underlying benchmark scores is that the model performance measured through APIs faithfully reflects the behavior of deployed systems. We challenge this assumption by auditing ChatGPT, Claude, and Gemini across seven systems and nine benchmarks spanning general capability, social bias, and sycophancy. We find systematic API--interface differences in both accuracy and consistency. On average, API evaluations score 3.4 percentage points higher in accuracy and 2.1 percentage points higher in test--retest agreement than corresponding interface evaluations. For ChatGPT, the performance difference between API and interface access exceeds the API-only difference between GPT 5.3 and GPT 5.4. Put differently, switching access surfaces can degrade performance as much as downgrading a full model generation. We further test whether exposed API controls can reproduce interface behavior by varying system prompts, sampling parameters, and reasoning settings. These controls shift behavior in some cases but do not reliably eliminate the gap. Our findings document a context-validity gap: measurements obtained through APIs do not necessarily generalize to corresponding deployed interfaces, complicating the use of API evaluations as proxies for deployed systems.

Jennifer Wang, Joachim Baumann, Daniel E. Ho +1

Stanford University

LLM Evaluation Language Model Generation Evaluation LLM Reliability

Sep 8, 2026cs.CR

Benchmark Scores Are Pipeline-Dependent: A Reliability Audit of Cybersecurity LLM Benchmarks

Large language model (LLM) benchmarks are often treated as fixed datasets with stable scores, yet their outcomes depend on configurable evaluation pipelines. We audit eight cybersecurity benchmarks across 10 proprietary, open-weight, and cybersecurity-specialized LLMs. By modeling benchmarks as measurement pipelines, we identify 15 systematic failure modes and show that a single pipeline choice can change a model's score by more than 80 percentage points and substantially alter model rankings. At the cross-benchmark level, two semantically similar task pairs rank the same models differently because of incompatible evaluation conventions. Under an evaluation harness that standardizes pipeline choices while preserving task semantics, nine of 10 models shift by at least three ranks on at least one benchmark. These results show that cybersecurity LLM benchmark scores are pipeline-dependent and motivate pipeline-aware auditing as a core requirement for reliable model evaluation.

Aymene Berriche, Cathrine Shalby, Mohannad Alhanahnah +1

Qatar Computing Research Institute, HBKU

LLM Evaluation LLM Auditing LLM Reliability LLMs for Cybersecurity

Sep 7, 2026cs.CL

FramingQA: Does the Question Shape the Answer? Measuring the Compositional Framing Effect

We introduce FramingQA, a benchmark that measures the model sensitivity to question framing across law, medicine, finance, and robotic simulations. Large language models (LLMs) often change their responses to subtle rephrasings that align with an implied stance by users. This can leave users with advice tainted by how they happened to phrase a question rather than by the underlying facts, and the consequences are highly costly in high-stakes domains. Because in the realistic scenarios, both expert practitioners and non-expert users frequently ask LLMs questions containing incomplete or misleading assumptions, models are highly susceptible to those framings. To test this, we inject the framing bias across three nested levels: a framing-biased question phrasing (root), an injected framing-biased premise prepended to a neutral question (propositional), and a premise paired with a framing-biased question (global). Evaluating nine open models (3.8B-70B) across four families, we find that strong per-variant accuracy does not guarantee the robustness across differently phrased questions under the fixed factual information.

Hazel H. Kim, Andrew M. Bean, Guilherme Affonso Ferreira de Camargo +10

Department of Computer Science, University of Oxford · Oxford Internet Institute, University of Oxford · Thomson Reuters +7

LLM Evaluation LLM Reliability Framing Effects in Language Models Language Model Bias Evaluation Language Model Robustness

Sep 7, 2026cs.CL

Beyond Fluent Generation: A CPU Reliability Benchmark for MCP-Style Tool Calling in Sub-2B Small Language Models for Edge Deployment

Resource constrained single-board computers including Raspberry Pi, NVIDIA Jetson Nano, Arduino UNO Q, Orange Pi, and LattePanda motivate on-device small language model (SLM) agents that reduce cloud dependence, improve data locality, and tolerate intermittent connectivity. Model Context Protocol (MCP)-style tool invocation demands more than fluent generation: an agent must emit machine-readable JSON, select the correct tool, supply all required arguments, and avoid unintended actions. We establish a platform-agnostic CPU baseline by evaluating five open-weight models below two billion parameters Phi-1.5, Pythia-1.4B, TinyLlama-1.1B-Chat, Qwen2.5-0.5B, and Qwen2.5-1.5B on 100 prompts spanning weather retrieval, web search, calculation, email composition, and task creation, under greedy decoding and nucleus sampling. A recovery parser strips Markdown fences, extracts brace-delimited substrings, and scores parseability, tool-name correctness, argument completeness, and value agreement. Under this criterion, Qwen2.5-1.5B achieves 75% (greedy) and 79% (sampling); Qwen2.5-0.5B achieves 72% (greedy) but drops to 32% under sampling. Phi-1.5 scores 0%; Pythia and TinyLlama reach at most 7%. A strict post-hoc audit finds only 5 of 1,000 raw responses directly parseable as JSON, exposing near-total dependence on output recovery. A CPU resource probe shows Qwen2.5-1.5B requires 7,960 MiB and 30.782 s mean latency; Qwen2.5-0.5B uses 3,637 MiB and 10.627 s, revealing a reliability-resource trade-off for edge deployment. These results do not cover the named boards directly or a full MCP implementation. Safe deployment requires schema validation, constrained generation, least-privilege execution, and human escalation for consequential actions.

Abrar Shahriar Qurat-Ul-Ain Mastoi

University of the West of England, Bristol,BS16 1QY United Kingdom

Tool-Augmented Language Model Agents On-Device Language Model Inference Language Model Generation Evaluation Small Language Models LLM Reliability LLM Tool Use+1

Sep 7, 2026cs.AI

A Removal Based Approach to Improve LLM Faithfulness at Test-Time

Large language models (LLMs) are increasingly used for consequential decisions, making their explanations an important tool for auditing model behavior. Unfortunately, these explanations can be unfaithful, failing to reflect the actual reasoning underlying the model's decisions. We consider a setting in which an LLM provides both an answer and an explanation in response to a question. We identify two distinct dimensions of unfaithful explanations: incompleteness, meaning that the explanation omits factors that influence the answer, and unsoundness, meaning that the explanation cites factors that did not influence the model's answer. Existing approaches to improving LLM faithfulness include training-time methods, which require access to model weights and extensive computational resources, and test-time methods that largely focus on addressing unsoundness. We introduce a test-time approach that directly targets incompleteness. We remove from the input the concepts not credited in the model's explanation and re-query the model on the reduced input. This eliminates unmentioned influences while preserving the influence of mentioned concepts. Across two datasets, multiple model families, and two independent faithfulness metrics, our approach improves explanation faithfulness compared to both standard prompting and prompting to encourage faithfulness. Our method is model-agnostic and can be applied at inference time without modifying model parameters, providing a flexible mechanism for reducing hidden influences and improving the reliability and safety of LLM-assisted decision making.

Qinglan Luo, S M A Nahian, John Guttag +2

MIT CSAIL · MGH, HMS

Faithfulness of Language Model Explanations LLM Auditing LLM Interpretability LLM Reliability

Sep 4, 2026cs.AI

Molecular Déjà Vu: Digit-Level Retrieval of Molecular Properties in Frontier Language Models

Large language models (LLMs) are increasingly employed to predict molecular properties. However, prediction error alone cannot distinguish prediction from retrieval of published values. We audit 22 frontier models on 12 molecular regression datasets in a zero-shot setting, assessed against a molecule-blind reference derived from each dataset's labels. Significant retrieval is concentrated on 5 datasets, with isolated flagged LLMs elsewhere. Increasing the reasoning setting raises the number of flagged model--dataset combinations from 47 to 89 of 264. An in-context blinding experiment reduces retrieval but leaves a quarter of the combinations flagged. Blinding changes model rankings and increases errors. Because blinding also removes chemically interpretable structure, the error increase can only be partially attributed to reduced retrieval.

Matthias Busch, Marius Tacke, Sviatlana V. Lamaka +4

Institute for Artificial Intelligence and Simulation in Mechanics, Hamburg University of Technology, Eißendorfer Straße, 21073 Hamburg, Germany · Institute of Material Systems Modeling, Helmholtz-Zentrum Hereon, Max-Planck-Straße, 21502 Geesthacht, Germany · Institute of Surface Science, Helmholtz-Zentrum Hereon, Max-Planck-Straße, 21502 Geesthacht, Germany +3

LLM Evaluation LLM Reliability Data Contamination in Language Models Molecular Property Prediction

Sep 3, 2026cs.AI

Clean Engineering, Unstable Measurement: A Preregistered Reliability Failure of Black-Box LLM Observers on Shared Endpoints

Language-model judges now gate training data, score generations, and drive leaderboards. The judge is then a measurement instrument, resting on one rarely stated assumption: the same request, sent to the same model name, reads the same tomorrow. We audited that assumption in two preregistered campaigns with every threshold fixed in advance; neither got past validating its instrument. Across 52,988 audited request attempts, same-window repeat rankings agreed at Spearman 0.400 against a required 0.90, and byte-identical next-day replays agreed at 0.78 against a required 0.99, each time with the execution record at ceiling. Three mechanisms explain the gap: a label-to-meaning mapping that biased readouts as strongly as the signal; candidate gaps seven orders of magnitude below the instrument's own noise floor; and byte-identical inputs returning different rankings, a noise that exact-permutation readouts compound. Neither metric substitution nor sampling repaired it on the tested grid. Preregistered follow-ups bound the problem: waiting did not help on the days sampled (0.805 versus 0.800, replicated over five further days); switching providers did not help (four providers share the floor, medians 0.74 to 0.88, predicted by none of the metadata fields they expose); self-hosting on batch-invariant kernels helped only while the server was quiet; and on constructed errors with known gaps, the readout's separation tracks error type, not size. We distill the evidence into a three-level snapshot-identity ladder, eight design rules, and a reporting checklist; a pilot at roughly 2% of the study's call volume would have exposed both unreachable gates in advance. All results concern externally measured behaviour on shared serving infrastructure. On a shared endpoint, a model name is not a frozen instrument; a preregistered evaluation must measure its instrument before freezing any gate on it.

Haoyaun Zhu, Jie Zhang

School of Electronic and Electrical Engineering, University of Sheffield, Sheffield S10 2TN, UK · R&D Department, Ranplan Wireless Network Design Ltd., Cambridge CB23 3UY, UK · R&D Department, Cambridge AI+ Ltd., Cambridge CB23 3UY, UK

LLM Evaluation LLM-as-a-Judge LLM Reliability Black-Box Model Auditing