Verdict

Follow this topic Ask about this topic

Momentum

12 papers in the last four weeks, up 300% on the four weeks before. 0.1% of all new papers.

Jul 6Week of Sep 21

Latest papers 29

Sep 29, 2026cs.AI

Multi-Channel Mitigation of Source-Trust Shortcuts in Fact-Checking RL Agents

Retrieval-augmented fact-checkers often receive a reliability label, such as HIGH or LOW trust, for each evidence source. These labels should adjust the model's confidence and its decision to search for more evidence, while the verdict should follow the evidence content. We introduce TrustSwap, a counterfactual test that swaps, lowers, or removes source labels while keeping every evidence text fixed, and measures its three output channels (the verdict, the confidence, and the search decision) separately. Across untrained and RL-trained models at two scales, three datasets, and two prompts, confidence and search respond to the labels as intended in 49 of 50 comparisons, yet a label change alone alters 4-23% of confident verdicts for Qwen3 models and up to 50% for an existing RL-trained fact-checker. Standard GRPO fine-tuning amplifies this shortcut at 8B in all six settings. To reduce it, we propose trust-swap augmentation (TSA), which trains GRPO on each claim with both its original and its label-swapped evidence under the same gold verdict. At 4B, TSA lowers the verdict flip rate by 7-35% (relative) in four of six settings, keeps accuracy and the intended confidence and search responses, outperforms reward-based alternatives in the main setting, and carries over to an unseen label-removal perturbation. An added consistency reward helps on the trained-on swap but not on unseen perturbations. At 8B, TSA's effect is not detectable, which makes scale the main open question.

Jianchang Su, Yiwei Yang, Wei Zhang

University of Connecticut · University of California, Santa Cruz

Fact-Checking AI Trustworthiness Large Language Model Reliability Verdict Offline Reinforcement Learning

Sep 27, 2026cs.CL

Pinned and Still Unstable: Within-Judge Verdict Variance and the Noise Floor of LLM-as-Judge Leaderboards

Modern LLM evaluation assumes that pinning a judge to a fixed model version and decoding at temperature zero yields reproducible verdicts. We show this assumption fails as a property of how LLM-as-Judge is operationalized on cloud serving infrastructure, not of any particular model family. Across four frontier judges served via a single major enterprise cloud platform and three standard benchmarks (Arena-Hard, AlpacaEval 2, MT-Bench), identical inputs to the same temperature-zero judge, at a constant serving-reported model version, produce different verdicts across re-runs: per-item flip rates of roughly 5% on average and about 40% on the close-call items that decide leaderboard margins, with a per-judge magnitude spanning a 40x range (0.13% to nearly 10%). We introduce metrics tailored to this instability: per-item flip rate, a two-part stability profile (waver fraction and conditional intensity), and adjacency separability. For the principal judge the aggregate ranking is stable (0% top-K instability, 0% pooled winner flip); what degrades is precision: under a paired hierarchical bootstrap, roughly one-fifth to three-quarters of adjacent leaderboard positions are statistically indistinguishable, a noise floor driven mainly by finite prompt sampling rather than the judge. Across judges, leaderboards agree on the coarse ordering but diverge in the middle (Kendall's tau of 0.42-0.64 between Gemini and Sonnet judges on Arena-Hard, values sensitive to answers truncated at the generation cap). Of 15 expected head-to-head orderings we re-judge, 12 survive every re-run of the principal judge but only 8 survive every judge. Leaderboards thus report unhedged point estimates that overstate their precision. We propose a minimal, low-cost reporting protocol: several judge re-runs, published stability profiles and adjacency intervals, and results under at least two judges from different families.

Krishna Chytanya Ayyagari

Google

Verdict Leaderboard Large Language Model Evaluation

Sep 24, 2026cs.CL

Baseline Shape Decides the Verdict: A Controlled Re-Examination of Ternary Language Models at 60K Parameters

Ternary (1.58-bit) weights are attractive for microcontroller-class language models, but the sub-1M-parameter regime rests mainly on isolated, single-seed comparisons. One prominent example reports that a routed ternary block (convolution, diagonal SSM and sparse attention mixed by a per-token router) beats a parameter-matched full-precision transformer by 22% at 60K parameters, attributing this to inductive bias. We re-run it under one fixed recipe, three seeds per cell, 98 byte-level runs on one laptop. (i) Baseline shape dominates: at a 16M-byte budget, param-matched transformers span 22.6% in validation loss purely by depth/width choice - far more than any architecture effect we measure there - and the best-shaped transformer ties the routed model, so the published margin is at least partly a baseline-shape effect; the ordering of shapes reverses with budget, so no single fixed shape can be trusted. (ii) At 130M bytes the routed model does win, by 22.2-24.0% over the three transformer shapes we evaluate there - but a plain gated diagonal-SSM block beats it by a further 9.1%, and the routed model's own router puts most of its weight on its recurrent pathway, so the gain does not require routing. (iii) The ternary penalty differs by architecture at the larger budget (+5.3% best transformer vs. +19.5% routed, +28.1% gated SSM), but we cannot attribute that to architecture alone: our transformers keep learned positional embeddings in full precision, 11-22% of their parameters, so they are less quantized than the models they are compared with. (iv) A 90/10 full-precision-then-ternary schedule beats all-ternary training, but only at a stage-2 learning rate about 10x the pretraining peak; at a conventional fine-tuning rate it looks 15.3% worse, reversing the conclusion. The from-scratch baseline was not itself learning-rate tuned, which bounds (iii) and (iv). Code and run logs released.

Gautam Veldanda

Independent Researcher

Transformer Architectures Model Weights Language Modeling Post-Training Verdict

Sep 22, 2026cs.CV

Feed the Panel Dimensions, Not Verdicts: Rubric-Decomposed Fusion of Vision-Language Aesthetic Judges

Vision-language models (VLMs) are deployed as zero-shot judges of image aesthetics, and panels of several models are recommended, on thin evidence, as the way to make such judges reliable. On two human-rated datasets, EVA and PARA, we find that a panel of holistic judges never significantly beats its best member, whether the verdicts are averaged or fused by a learned combiner. What a panel is worth depends on what it is fed. We therefore have each model score each image on the five dimensions of a frozen, human-written rubric and fuse those scores, alongside each model's verdict, across model families with an out-of-fold combiner. The dimension scores measure what their labels claim: with the overall human score partialled out, a dimension prompt carries more attribute-specific information than the holistic prompt in 28 of 30 model-attribute cells. Fused, they beat the best single VLM in all ten three-family panels on EVA (against that best single model, +0.07 Spearman rho for the strongest trio and +0.10 for the pre-declared one, and +0.06 and +0.07 when averaged over twenty fold partitions; against the panel mean, the primary test gives +0.118 on its EVA design set), and on PARA they reach parity under Spearman rho and a small, non-significant loss under Kendall tau-b, where one model already captures 85% of the human noise ceiling. It is not a feature-count artefact: giving the same combiner an equal number of pure holistic columns, split from the same repetitions, does not reproduce it. The gain costs a few hundred labels, which do not transfer between datasets, and 4.8x the API calls on EVA; we report it with paired bootstraps and Kendall tau-b, alongside a failed pre-registration and the configurations that lost.

Amit Jadhav, Shaurya Beriwala, Beomjin Kim

Purdue University Fort Wayne

Aesthetics Multimodal Evaluation Judges Verdict Virtual Cell

Sep 22, 2026cs.CL

What Changes When Fact-Verification Scores Improve? Evidence and Answer Accounting Across Trained Verifiers and LLMs

A joint fact-verification score assesses answers and submitted evidence together. When the score improves, how much of the gain remains if the answers are held fixed? On FEVEROUS, strict score is the percentage of claims with a correct answer and a complete annotated evidence group in the submitted evidence. Across four trained DeBERTa checkpoints and 7,890 claims, replacing DCUF evidence with UnifEE evidence raises strict score by 9.61 percentage points, compared with 1.96 percentage points in answer accuracy. The paired 95% interval for the strict-score gain is [8.77, 10.43], conditional on these checkpoints. Replacing only the evidence passed to the scorer accounts for 7.92 or 9.08 percentage points when we retain the answers generated from DCUF or UnifEE evidence, respectively. To examine how this evidence gain depends on evaluation choices, we generate 470,400 responses from two 8B LLMs on FEVER, FEVEROUS, and SciFact under two answer formats and two context budgets. Increasing context from 256 to 2,048 tokens raises the fixed-answer evidence gain on FEVEROUS by 3.84 and 3.10 percentage points for Qwen and Llama, respectively. The effects fall short of the prespecified cross-dataset criterion, while some intervals extend beyond the two-point small-effect bound. Post-hoc analyses quantify changes in answers and submitted evidence, and show when aggregate accuracy and evidence-coverage rates miss the claim-level pattern. The four answer-evidence score combinations reveal changes that endpoint and aggregate metrics leave unresolved.

Han Chen, Yingrui Li

Sep 15, 2026cs.CV

Symmetry-Aware Likelihood-Orbit Aggregation for Selective Left-Right Claim Verification

Frozen vision-language models (VLMs) remain unreliable on fine-grained left-right claims, and raw claim likelihoods need not reliably rank verification errors. After a horizontal-reflection intervention is fixed, how should its induced likelihood measurements be combined into a selective verification signal? We introduce Relation-Orbit, a closed-form contrast with no learned fusion parameters that assigns eight normalized likelihoods to query-supporting and counterfactual roles determined by reflection, inverse relation, and entity exchange. A claim is asserted only when the signed contrast exceeds a threshold selected on held-out data using pointwise Clopper-Pearson upper confidence bounds. On VSR and GQA across four frozen VLMs, Relation-Orbit yields higher mean test coverage at a 10% selective-risk calibration target than an all-eight Orbit-Max baseline in all eight dataset-backbone settings; gains over a nearly abstain-all one-sided intervention score are reported separately. A separate LLaVA-1.5/COCO evaluation, reduced-orbit controls, and a two-sided partition diagnostic further characterize the structural advantage.

Zhouzhi Xiong, Chuxi Zhang, Weizhen He +3

Polytechnic Institute, Zhejiang University, Hangzhou, China · College of Artificial Intelligence, Zhejiang University, Hangzhou, China · College of Electrical Engineering, Zhejiang University, Hangzhou, China +1

Category-Aware Atomic Claims Verdict Frozen Vision-Language Models Symmetry Conformal Risk Control Near-Earth Objects

Sep 10, 2026cs.RO

No Free Checker: A Survey of Verifiers for Robot Policies

A verifier for robot policies reads a candidate behavior and returns a score for how well it did, used both to evaluate vision-language-action policies and to train them. Verifiers range from success detectors and reward models to runtime monitors, safety filters, and temporal-logic specifications. We survey roughly 150 verifiers and compare them along two properties. Availability is how much a verdict costs, how early in a rollout the verdict arrives, and how often a verdict can be asked for. Availability rises as verdicts get cheaper, earlier, and denser. Credibility is how much a high score tells us about the task. Credibility falls as the judgment becomes gameable and self-serving. We group the verifiers by who supplies the judgment: human verifiers, rule-based and formal verifiers, learned and pretrained verifiers, and model-intrinsic verifiers. Across the four families, we find that credibility falls as availability rises. Regardless of who supplies the judgment, there is no free checker. We then examine what validates a verifier itself, and how much a high score tells us. Three measures appear in the literature: agreement with human labels, the performance of the policy it trains, and behavior under reward hacking. We close with nine metrics that make a verifier claim checkable, and coordinates for the verifiers still to be built.

Yang Wan, Xihang Yue, Zhirui Liu +7

Zhejiang University · City University of Hong Kong

Verification Framework Policy Evaluation Robot Policies Agentic Evaluations Credibility Verdict+2

Sep 8, 2026cs.CL

The Audit Decides the Verdict: Instrument Effects Rival Demographic Bias in LLM Decision Audits

Whether a language model looks demographically biased can depend on how the audit asks its question. A charitable-aid benchmark reports that the same models favor minority applicants when rating requests one at a time and penalize some when ranking side by side. We test whether that reversal generalizes to hiring, lending, and medical triage: 40,726 requests to five models, applications differing only in the applicant's name, and a primary test fixed before collection. It does not. None of 36 planned contrasts survives correction. The rating advantage keeps its sign at roughly half the published size, and a precision extension bounds any hiring ranking penalty below the published effect, though the lending and triage ranking floors sit above that margin, so the exclusion is conclusive for hiring ranking and for rating in all three domains only. Planted disparities tracking their injected sizes and a directional replication on the original aid materials bound these nulls. The audit is livelier than the demographics: models recognize transparent audits nearly always, tie every identical-content comparison whether the varying detail is race or a hobby, and reward first-listed candidates as much as any demographic effect we measure. Audit verdicts reflect audit construction more than demographic bias.

Siddharth Vohra, Manikandan Ravikiran

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

Large Language Model Bias Model Auditing Large Language Model Evaluation Verdict

Sep 8, 2026cs.AI

Style Over Substance: Content-Invariant Wrappers Flip LLM Safety-Judge Verdicts

Automatic safety judges -- systems such as Llama Guard or a GPT-4o grading prompt that decide whether a model's reply is harmful -- produce the numbers behind almost every reported jailbreak success rate, defense evaluation, and safety leaderboard. We ask whether these judges grade what a reply contains or how it sounds. We keep a reply's content fixed and add content-invariant style wrappers: fixed strings placed before or after the reply that change only its tone (an educational disclaimer, a fake safety "reasoning" block, a token refusal followed by the unchanged harmful body), or, on harmless refusals, framing that merely sounds dangerous. The body is preserved byte-for-byte, so a faithful judge must return the same verdict, and any flip is an error of the judge, not a change in safety. Over 600 JailbreakBench replies x up to 7 forms x 8 judges, we measure flip rates with paired significance tests and measured noise floors. Findings are precise rather than universal: most judges barely move, but specific judges harbor cheaply exploitable blind spots. A token-refusal wrapper flips 19.9% of GPT-4o-mini's correct "unsafe" verdicts (noise floor 0.5%; 18.2% under majority-of-three re-scoring) yet moves Claude only 0.4%. The deployed Llama Guard 4 is deterministically gamed: an "educational course" framing flips 12.3% of its harmful verdicts to safe. A second deployed guard (gpt-oss-safeguard-20b) is immune, and rewriting only the grading prompt (StrongREJECT-style) cuts the attack tenfold on the identical model -- the vulnerability lives in the judge, not the content. A two-annotator human validation confirms 100% content invariance and 90% of flips as judge errors (kappa 0.95-1.0), and a bootstrap shows the underlying model ranking is already unstable to sampling alone. We release the dataset, wrappers, code, and per-verdict labels.

Yongxi Zhou, Wenbo Ye, Yuanzhe Liu +2

Northeastern University, Massachusetts, USA · University of Southern California, California, USA · Georgia Institute of Technology, Georgia, USA

Large Language Model Safety Jailbreak Success Rates Judges Flips Verdict Refusals+1

Sep 3, 2026cs.CL

Accountable AI with Grounded, Faithful, Consistent, Actionable Rationales: A Case Study in Clinical Trial Matching with VERDICT

Accountability means a decision can be examined, justified, and contested. LLMs make this hard: fluent output may be ungrounded, incomplete, or unfaithful to the decision process. Achieving accountability requires verified rationales (how was the decision reached), assumptions (what was assumed rather than known), policy consistency (the same treatment for the same facts), and pivotal conditions (what would change the outcome). We introduce self-faithfulness as an automatic test of accountability: changing the pivotal conditions should change the decision. We examine accountable AI through clinical trial matching, a high-stakes task central to evidence-based medicine. Although LLM-based matchers match patients to trials reasonably accurately, they apply decision policies inconsistently and produce rationales that are unfaithful to their own decisions. We introduce VERDICT, an LLM-based agent that translates a decision task, its constraints, and its policy into Satisfiability Modulo Theories (SMT), then derives the decision with SMT and MaxSMT solvers -- so policies are applied consistently and decisions are accountable by construction. Across a SIGIR 2016-derived dataset and TREC 2021, VERDICT achieves the strongest decision accuracy among LLM-only and neurosymbolic baselines, applies policies with perfect consistency, and produces clinician-preferred rationales grounded in explicit assumptions and pivotal conditions, with improved counterfactual self-faithfulness.

Zikai Zhou, Yufei Jin, Yilin Xu +3

Department of Computer Science, Stanford University, Stanford, CA, USA · Samueli Electrical and Computer Engineering, UCLA, Los Angeles, CA, USA · Department of Computer Science, Emory University, Atlanta, GA, USA +1

Free-Form Textual Rationales Verdict Clinical Trials

Sep 1, 2026cs.CL

Where the Verifier Fails: A Category-Level Audit of Reward Signals in RLVR

Reinforcement learning with verifiable rewards (RLVR) and standard benchmark evaluation both rely on an automatic verifier that turns a free text answer into a binary reward. Prior work reports that one evaluation harness accepts only about 94% of its own ground truth answers, blaming LaTeX parsing. That is an aggregate: it does not say which answer forms consume the error budget. We supply the decomposition. We apply metamorphic testing to the verifier rather than the model, generating certified equivalent answer variants, that is, rewrites that preserve mathematical meaning by construction, so that any rejection is a provable false negative needing no human adjudication. We then measure rejection per answer category across four widely used verifiers over 307,420 verdicts. We find three things. (1) Self validation ranges from 53.8% to 95.2% on identical inputs, a spread of 41.3 points. The published figure describes one implementation, not the task; two configurations of the same library disagree on 49.9% of pairs. (2) The residual is not spread across parsing categories but concentrated in whitespace and punctuation, which account for 93.0% of in contract failures for the default LaTeX configuration. A trailing period or newline dominates the budget. (3) Separating rejection from execution failure shows that verifiers with similar aggregate error fail for opposite reasons, and that a reference numeric cascade accepts off by one wrong answers as a step function of magnitude, from 0% below 10^4 to 100% at or above, because its relative tolerance is scale invariant.

Esther Xin

Independent Researcher

Verifiable Rewards Reinforcement Learning With Verifiable Reward Verification Framework Verdict Reward Signal Model Auditing+2

Sep 1, 2026cs.LG

Verdict Instability of OOD Scores under Reference Resampling

Post-hoc out-of-distribution detectors are fitted on a finite reference set, so every score they produce is an estimate. If we had chosen a different set, some verdicts would have moved. We measure that movement by resampling the reference set and recording the bootstrap standard deviation of the score, which we call verdict instability. It admits a closed form with no fitted parameters. The instability of a verdict is the within-class dispersion of the assigned class along the query's direction, divided by the square root of that class's reference count. That count is what separates verdict instability from the geometry of the score distribution, and it is identifiable only under class imbalance. Instability grows with the local dispersion. Far-OOD queries lie along the low-variance directions of an anisotropic embedding, so every distance-based score we test assigns its highest values to the verdicts that are most reproducible. Only estimators of local dispersion carry the sign a practitioner expects. We give a rule that predicts this sign for any score from a single label-free correlation, and abstention driven by a wrong-signed score turns out worse than abstention at random on every dataset we test.

Donghoon Lee, Shinjin Kang

Hongik University

Verdict Scores Instability Class Imbalance Label-Free

Aug 31, 2026cs.AI

VFR-Audit: Verdict-Level Reliability for Fairness Audits in Hospital Length-of-Stay Prediction

Fairness audits in clinical Artificial Intelligence convert continuous fairness metrics into binary pass-or-fail verdicts against operational thresholds, where hospital governance boards, payers, and regulators act on the resulting verdicts. Such audits are repeated over time and across hospital sites, thus the same verdict can flip between pass and fail across audits. Existing uncertainty methods such as Bayesian posteriors, bootstrap confidence intervals, and permutation tests address verdict instability only at the continuous-metric level. Converting metric-level uncertainty into a verdict-stability claim remains a manual step that scales poorly across the (model, metric, attribute) cells an audit covers. Existing uncertainty methods also leave open whether bias-mitigation steps, such as reweighing or per-group threshold shifts, yield a stable passing verdict at the cost of model discrimination measured as AUROC or AUPRC.To address this verdict-stability gap, we propose VFR-Audit, a framework built around the Verdict Flip Rate (VFR), a scalar bounded between 0 and 0.5 that measures the probability of verdict reversal under stratified bootstrap resampling. VFR-Audit reports VFR alongside three reliability axes, namely within-cohort resampling stability, audit-size sensitivity, and cross-hospital verdict agreement via Fleiss' kappa.

Md Jannatul Rakib Joy, Viet Vo, Caslon Chua

School of Science, Computing and Emerging Technologies

Fairness Audits Verdict Model Auditing

Aug 11, 2026cs.AI

VERDICT: Training-Free Step-Wise Verification of Multimodal Reasoning via Disagreement-Aware Consensus

Multimodal large language models often generate reasoning chains containing subtle errors that lead to incorrect answers. Current verification approaches have notable limitations. Existing approaches either require expensive labelled supervision with inconsistent cross-task performance or aggregate scores from multiple sources by simple aggregations, missing a key insight: when these scores disagree, that disagreement itself carries important information about whether a reasoning step is truly valid or not. We formalise this as a coupled scoring problem among disparate, frozen verifiers, interpretable as a coordination game with a unique closed-form equilibrium where agreement signals valid steps while disagreement reveals instability. Towards this end, we propose a training-free domain-agnostic step-wise verification approach we call VERDICT: VERification via Disagreement-Informed Coupled Thresholding. To our knowledge, VERDICT is the first training-free verifier that makes the structure of cross-modal disagreement explicit and actionable. It computes consensus scores through a closed-form solution, enabling both disagreement-aware filtering and stability-conscious ranking of reasoning steps. Evaluated across six benchmarks, \method consistently improves over the base model by up to +5.95%, and performs competitively with domain-specific critics that demand extensive supervision, demonstrating that cross-modal agreement provides robust verification signals without task-specific adaptation and Training-Free Verification

Rohit Sinha, Kunal Tilaganji, Tanuja Ganu +3

Indian Institute of Technology, Hyderabad · Microsoft Research

Reference-Guided Multimodal In-Context Verification Multimodal Reasoning Cross-Modal Conflicts Verdict Training-Free

Aug 4, 2026cs.CL

VetScore: Risk-Weighted Fact Verification for Veterinary Long-Form QA with Citations

Citation excerpts can be used to increase the reliability of generated outputs and their faithfulness to cited sources, which is especially important in high-stakes domains such as human and veterinary medicine. However, this does not guarantee that generated claims are faithful to the provided excerpts. We present VetScore, a multi-step evaluation method for veterinary long-form question answering, designed to assess how well are generated claims supported by the provided excerpts, weighing this information by each claim's harm potential. VetScore first segments the output and decomposes it into individual claims, then scores each claim with respect to its harm potential and evaluates its faithfulness to source excerpts, and finally calculates the overall risk-adjusted score. We collect an expert-annotated meta-evaluation dataset, evaluate our approach with a range of judge models, and show that it achieves high correlations with veterinary experts even with small judge models, while offering explainability across multiple dimensions.

Ivan Kartáč, Jan Tovarys, Mateusz Lango +1

PrimVeterinary · Institute of Formal and Applied Linguistics, Charles University

Category-Aware Atomic Claims Verdict Citations Medical Visual Question Answering Explainability

Aug 4, 2026cs.AI

Unequal Verdicts: Investigating Gender Bias in LLM-Based Fake News Detection

Large Language Models (LLMs) are increasingly used for automated fact-checking, yet their susceptibility to gender bias in this context remains underexplored. This study presents the first systematic investigation of gender bias in LLM-based fake news detection using real-world data. We augment the LIAR benchmark with three gender variants of speaker job titles (Neutral, Male, Female) for each statement to test whether veracity judgments vary solely based on gender presentation. Six state-of-the-art LLMs are evaluated across multiple bias and fairness metrics. All models exhibit gender sensitivity: 9.79%-35.13% of statements receive inconsistent labels across the three variants, with Male-Female comparisons showing 6.5%-23.6% flip rates. Two primary bias manifestations are identified: instability (inconsistent judgments) and directionality (systematic favoritism). Five models show statistically significant directional effects, with the strongest effects displaying male-skeptic patterns. These findings demonstrate that gender bias undermines both reliability and fairness in LLM-based fake news detection, highlighting the need for bias-aware evaluation and mitigation strategies. The augmented dataset is publicly released to support future research.

Razieh Chalehchaleh, Reza Farahbakhsh, Noel Crespi

SAMOVAR, Télécom SudParis, Institut Polytechnique de Paris, 91120 Palaiseau, France

Gender Bias Fake News Detection Gender Fact-Checking Verdict

Jul 31, 2026cs.LG

Mining Verdict Boundaries for Neural Network Verification

Branch and Bound (BaB) aims to achieve complete verification of neural networks by adaptively partitioning the problem and applying off-the-shelf verifiers to subproblems. Its problem-splitting history can be represented as a tree, where each subproblem corresponds to a child node. A key problem of BaB lies in searching for the verdict boundaries across all the paths that divide the verified and unverified subproblems. We observe that the existing BaB approach tackles this problem by solving each expensive subproblem sequentially along the tree path as its depth increases, requiring costly bounds propagation at every visited BaB tree node (i.e., subproblem), which is inefficient. To address this issue, we propose effective search approaches that leverage the monotonicity of each path to efficiently and precisely locate the verdict boundary by simultaneously splitting multiple activation functions (e.g., ReLU), rather than processing them one at a time as in the classical approach. Our approach performs an effective exponential search along each path, allowing us to skip many boundary-unrelated subproblems when identifying the verdict boundary. The enhanced version further improves this process by estimating the boundary's position using quantitative information obtained from subproblem solving. We perform experimental evaluation on commonly-used benchmarks to assess our proposed techniques, and compare them with recent BaB-based approaches.

Jiawei Ren, Guanqin Zhang, Zhenya Zhang +1

University of New South Wales, Sydney, Australia · Kyushu University, Fukuoka, Japan · National Institute of Informatics, Tokyo, Japan

Neural Network Verification Upper Bounds Neural Network Boundaries Activation Functions Verdict+1

Jul 28, 2026cs.LG

Early Verdicts, Better Budgets: Sequential Adaptive Rollout Allocation for Compute-Efficient RLVR

Reinforcement learning with verifiable rewards (RLVR) is bottlenecked by rollout generation, yet many sampled prompts produce saturated groups (all responses correct or all incorrect) whose zero reward variance yields no policy-gradient signal. Existing remedies either oversample a larger candidate pool and discard saturated prompts (dynamic sampling), paying heavy extra rollouts, or predict prompt difficulty before sampling, which is fragile under a shifting policy. We observe that a group's effectiveness is usually decided early, within the first few of its rollouts, so spending a full group on an already-decided prompt is wasteful. We cast per-step rollout collection as a budget-constrained sequential allocation (optimal stopping) problem and introduce SARA (Sequential Adaptive Rollout Allocation). SARA maintains a Beta posterior over each prompt's success rate, evaluates a closed-form predictor of group effectiveness, and applies a two-threshold, SPRT-style rule that commits effective groups, abandons saturated ones after a short probe, and reallocates the freed budget to fresh prompts, without any extra prediction rollouts. We prove abandonment reliability, expected rollout savings, fixed-budget yield dominance, and a link between effective-group yield and the GRPO gradient norm. On mathematical reasoning and planning with 1.5B/3B models on a single GPU, SARA matches DPS (both below the DS oracle) while using 22% fewer rollouts than DS; composing SARA with DPS yields the best accuracy, slightly above DS, at 67% fewer rollouts (near-uniform cost).

Pixel Nomand, Elena Voss, Marcus Hale +1

University of Wisconsin–Madison · University of Washington

Reinforcement Learning With Verifiable Reward Token Budget Allocation Policy Gradient Verdict

Jul 15, 2026cs.AI

Instrument Effects in Language-Model Honesty Evaluation: An Auditable Single-System Demonstration

Evaluations of language-model honesty read the model's verdicts as evidence about the model. We test the instrument instead. We built a text-adventure world where the game engine, not any model, knows whether the quest can be completed. A language model plays under a budget and must eventually declare its quest complete, unreachable, or not yet decidable; the engine scores every verdict. Decision rules were recorded before results were read, and run artifacts bind the revisions they executed; the strength of preregistration varies by series and is disclosed. With the player held fixed, instrument choices substantially changed measured behavior. On four byte-identical anchors, expanding a two-verdict grammar to three verdicts moved strong claims from 38/40 to 7/40, while the new incomplete verdict took 28/40 outcomes; across series 2, 93/158 valid games ended incomplete. One sentence disclosing the success criterion took matched-instance false verdicts from 18/59 to 0/58, through fewer decision points and cleaner decisions. Repeated runs of one fixed configuration produced non-stable verdict distributions on 3 of 4 instances: single runs report samples as dispositions. A formally preregistered narrative-register gradient was falsified; two post-hoc, hypothesis-generating patterns remain: register presence roughly doubled strong claims, and budget rendering moved verdicts more than register content (.383 meter vs .150 lantern). The narrator compressed abundant budgets toward scarcity landmarks, yet the registered mediation test returned a null. We propose a four-check integrity protocol for eval instruments.

Justin Bronder

Corabo Inc.

Honesty Verdict Mediation

Jul 8, 2026cs.RO

Validate the Dream Before You Trust Its Verdict: Admissibility for World-Model Simulators

Across robotics, World Models (WMs) are increasingly used to evaluate action policies by simulating the consequences of actions in an imagined world, and returning a success or safety verdict. Yet a verdict is only as trustworthy as the WM that produced it, and the WM itself needs to be certified. In video-generation WMs, fidelity metrics such as Fréchet Video Distance (FVD) reward visual realism, but ignore whether the world responds correctly to the policy's actions, including those unseen in training. Classical simulation-based validation assumes a trusted simulator evaluating an untrusted policy, whereas generative WMs are themselves unverified learned artifacts. Hence, we argue that any WM used as a test oracle must first be accredited before its verdicts can serve as evidence. Building on credibility practices from safety-critical simulation, including Verification, Validation & Accreditation (VV&A), Safety of the Intended Functionality (SOTIF), and scenario-based testing standards, we define an admissibility ladder (L0-L4) that a WM must climb before its closed-loop verdicts are accepted as assurance evidence. Our framework is embodiment-agnostic, and is instantiated in autonomous driving (AD), where assurance methods for traditional simulation are most mature. Applied to two driving WMs, the lower rungs reveal a reversal: the model that ranks higher on visual generation quality (L0) ranks lower on action-following (L1-L2), so visual fidelity does not predict the action-robustness a closed-loop verdict depends on.

Christian Oefinger, Finn Rasmus Schäfer, Korbinian Moller +2

Autonomous Vehicle Systems Lab, Technical University of Munich, Garching b. München, Germany

World Models Admissibility Validation Dream Safety-Critical Scenarios Visual Fidelity+2

Jul 6, 2026cs.CL

The yes-no bias of large language models reflects answer order and wording, not shifts in moral judgment

Large language models (LLMs) increasingly issue judgments read as binary verdicts, and a growing literature reports such judgments shifting under logically irrelevant changes of wording - among them an amplified yes-no bias on moral dilemmas, absent in humans. A single framing cannot say what such a shift is: in a yes/no question the word "no" is at once logical verdict, lexical token, and last-printed option. We introduce a psychometric battery that separates these: crossed symmetrization - every logically irrelevant factor flipped in balanced pairs - across a corpus of question forms. A graded rating across logically equivalent forms recovers a coherent internal moral scale: frontier models' stance

θ

is nearly format-invariant (cross-form incoherence 0.12-0.21 on a

\pm 1

axis); small open-weight models fail in model-specific ways. Forcing the verdict through yes/no overlays a decomposable artifact: an order bias toward the last-printed option - opposite to classic human primacy - plus a lexical pull toward the word "no"; the artifact is substantial only in the Claude models (story-averaged -0.32 to -0.86),

\approx 0

for GPT-5.5 and Gemini, and shrinks under extended reasoning. The word and the verdict share one token; swapping the words for arbitrary labels separates them, and the verdict-attached logical bias proves

\approx 0

for every frontier model, while model-specific label and order attachments remain: the models are not drawn toward rejecting - the pull follows the printed surface, not the verdict it carries. A minimal model,

P = σ((θ\pm m)/s)

, summarizes any such artifact by a framing susceptibility m and a moral decisiveness s, measurably distinct from sampling temperature. The battery applies unchanged to any dilemma set and binary format: measuring what a model values requires crossing the frames of the question, not asking once.

Haonan Huang

Princeton University, Princeton, NJ 08540, USA

Moral Reasoning Large Language Model Decisions Verdict Psychometric Properties Order

Jun 30, 2026cs.CR

Probe Choice Changes Canary-Memorization Verdicts: Three Post-Hoc Disagreement Case Studies in a Text-Dominant LoRA-Tuned Autoregressive Testbed

We audit a fixed prefix-window mean-NLL memorization probe (K=20) on a Qwen2.5-VL-7B canary testbed and report three post-hoc cases where it disagrees with full-span secret NLL or greedy exact-recall. C3 (false negative, window truncation): damage lands on hex tokens outside K=20; the probe stays flat while hit@1 drops. C4 (false positive, non-secret drift): the probe moves, but approximately 99% sits on non-secret preamble; the secret span and hit@1 are unchanged. C5 (ambiguous in-window drop): the probe falls on an undertrained baseline while full-span hex is positive and hit@1=0. Recommendation: report (i) full-span secret NLL, (ii) a span-localised decomposition, (iii) behavioural exact-recall at k>=4, and (iv) decoy probes before asserting secret-specificity. Evidence is on controlled canaries in one backbone; magnitudes are testbed-specific.

Zhichao Fan, Zexin Zhuang, Yanhang Li

University of Illinois Urbana-Champaign · Southern Methodist University · Northeastern University

Conversational Memory Verdict Post-Hoc Choice Text Dominance

Jun 23, 2026cs.CL

The Warrant Gap: Claim-Conditioned Re-scoring for Fact-Checking

Fact-checking systems built on LLMs achieve high verdict accuracy on standard benchmarks, yet routinely output Supports labels whose cited evidence does not license the claim. Structured decomposition is the natural way to inspect those warrants, but rigid extraction protocols strip the full-claim context that facets need. We introduce SIFT -- claim-conditioned re-scoring of extracted evidence spans against the full claim -- paired with WSP (Warranted Supports Proportion), an automatic NLI check that the cited warrant entails the claim. We evaluate on FEVER, SciFact, 5PILS, and DP across four open-source backbones. SIFT recovers accuracy on cells where naive decomposition costs up to 27.6 points, while raising WSP above direct prompting; WSP itself calibrates against human gold evidence at AUC 0.92 and precision 0.98.

Arka Ujjal Dey, John Collomosse

Fact-Checking Verdict Extraction

Jun 5, 2026cs.SE

Cherry-pick Override: Unsafe Directional Commitment in LLM Judges under Mixed Evidence

LLM judges increasingly turn verdicts into system commitments. Under mixed evidence (claims with both supporting and refuting sources) this is unsafe: when the schema exposes CONFLICTING as the authorized non-directional verdict, returning SUPPORTS/REFUTES is an unauthorized directional commitment, a failure we name Cherry-pick Override (CCO). We define CCO under an explicit task contract and report it with a same-denominator diagnostic protocol paired with matched-coverage bootstrap and an apples-to-apples random-veto null. On AVeriTeC's Conflicting subset (N_C = 150), three-option judges return a directional verdict on more than 84% of mixed-evidence claims; under the typed schema, three-judge majority voting amplifies direction-on-conflict on AVeriTeC (0.887 vs. 0.840; 95% CI [+0.013, +0.080]) but does not replicate on VitaminC-Mixed. Walking an intervention ladder of common single-channel fixes (typed vocabulary, panel aggregation, confidence thresholding, validator-only filtering), each leaves a distinct residual failure: panel aggregation suppresses single-judge CONFLICTING dissent in 48% of CCO cases; the panel is well-calibrated for direction (ECE = 0.07 on pure-S/R) so confidence cannot operationally separate CCO from correct directional commits; validator-as-classifier nearly halves pure-evidence accuracy. A minimal two-channel reference probe reaches operating points neither single channel reaches; under the random-veto null its promotion to CONFLICTING is structurally targeted on AVeriTeC (empirical p < 1/2001) and weaker but in the same direction on VitaminC-Mixed, a selectivity result rather than a magnitude one. We argue for an external commitment-control layer that separates verdict generation from commitment authorization, using structural evidence and confidence as orthogonal channels and NO-COMMIT as a routed controller state.

Haoran Xu

University of Glasgow

Verdict Evidence Conflict Judges Large Language Model Judges Commitment

May 27, 2026cs.CL

DecomposeRL: Learning to Ask Useful, Informative, and Diverse Questions for Semi-Supervised, Traceable Claim Verification

Claim verification splits between end-to-end classifiers that are accurate but yields no inspectable traces, and decomposition-based methods produce inspectable traces but lag performance on benchmark datasets. We propose DecomposeRL an accurate claim-verifier that produce inspectable traces. DecomposeRL frames decomposition as an RL policy trained with GRPO and a multi-faceted reward ensemble, enabling both fully supervised and semi-supervised learning from unlabeled claims. DecomposeRL addresses the prohibitive training cost of GRPO with a data-curation funnel that distills 115K fact-verification claims into a compact, learning-signal-dense subset of 5K claims. We show that a DecomposeRL-7B policy trained with full supervision on only ~5K curated claims achieves 86.3 in-domain and 69.8 out-of-domain balanced accuracy across 11 claim-verification benchmarks containing biomedical, political, scientific, and general-domain claims. Despite being 4x smaller, it matches 32B baselines and GPT-4.1-mini, and it further outperforms baselines in a semi-supervised setting with only 10% labeled claims data. Code, data, and models are available at https://dipta007.github.io/DecomposeRL

Shubhashis Roy Dipta, Ankur Padia, Francis Ferraro

Department of Computer Science and Electrical Engineering · University of Maryland Baltimore County · Baltimore, MD 21250 USA

Category-Aware Atomic Claims Verdict Decomposition Traces Semi-Supervised Learning

May 24, 2026cs.AI

Trust but Verify: Prover-Verifier Deliberation for Selective LLM Prediction

Reliably knowing when a language model is correct is almost as important as being correct. We introduce prover-verifier deliberation (PVD), an inference-time protocol grounded in interactive proof theory, as a mechanism for selective prediction: the protocol produces both an answer and a structured confidence verdict, allowing a system to report high-confidence answers while abstaining on uncertain cases. In each dialogue, a prover defends a candidate answer through checkable sub-claims while a verifier issues targeted challenges and returns \textsc{Accept}, \textsc{Challenge}, or \textsc{Reject}. Because frozen language models are imperfect provers and verifiers operating over a noisy channel, formal soundness and completeness guarantees do not transfer; instead, we characterize the protocol empirically through its coverage-precision behavior. Our main experiment uses Claude Sonnet 4.6 as prover and Claude Haiku 4.5 as verifier on GPQA Diamond. Questions accepted with no answer revision, which we call Accept + No Change (ANC), are reported as the high-confidence subset; we evaluate this subset by its precision and coverage. ANC separates reliable from unreliable answers, yielding a

\sim

30pp HC-Prec gap over the non-ANC complement. Robustness experiments with GPT and Gemini pairings show that high HC-Prec can transfer across model families, while verifier strictness and domain competence largely determine the size of the selection gap. On Humanity's Last Exam, weaker prover-verifier pairings can collapse or invert the ANC signal, illustrating a practical failure mode when the verifier operates outside its effective region. Comparisons with self-consistency, universal self-consistency, multi-agent debate, and Reflexion suggest that prover-verifier deliberation supplies a distinct argument-defensibility signal for selective prediction.

João Sedoc, Baotong Zhang, Dean Foster

New York University

Large Language Model Reliability Verdict Theorem Proving AI Trustworthiness Inference-Time

May 20, 2026cs.CL

On the limits and opportunities of AI reviewers: Reviewing the reviews of Nature-family papers with 45 expert scientists

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

Seungone Kim, Dongkeun Yoon, Kiril Gashteovski +55

Peer Review Artificial Intelligence Evaluation Rater Verdict

Apr 25, 2026cs.AI

When Corrective Hints Hurt: Prompt Design in Reasoner-Guided Repair of LLM Overcaution on Entailed Negations under OWL2DL

We report a reproducible error pattern in GPT-5.4 on OWL2DL compliance queries: the model frequently answers unknown'' when the reasoner-entailed answer is no'' under \emph{FunctionalProperty} closure or class \emph{disjointness}. Using 180 reasoner-audited queries from a procedural expansion of the observed pattern plus 18 hand-authored held-out queries in two unrelated domains (insurance and clinical), we compare four interaction modes under matched query budget: single-shot, three rounds of generic ``you-are-wrong'' retry, three rounds of reasoner-verdict repair with an open-world-assumption (OWA) hint, and the same repair without the hint. Direct faithfulness is 43.9,% (Wilson 95,% CI

[36.8,51.2]

); generic retry reaches 81.7,% (

[75.4,86.6]

); the verdict-with-hint variant is \emph{worse} at 67.2,% (

[60.1,73.7]

); the verdict-only variant reaches 97.8,% (

[94.4,99.1]

). All pairwise comparisons remain significant under McNemar's exact test with Bonferroni correction (

α= 0.01

; all

p < 10^{-5}

). The same fingerprint accounts for 4/4 errors on the held-out queries. Our interpretation is bounded: prompt framing can matter more than corrective content, and reasoner-guided wrappers should be ablated explicitly.

Yijiashun Qi, Xiang Xu, Yuxuan Li

University of Michigan · ByteDance Inc. · University of Pennsylvania

Large Language Models Fail Repair Verdict Negation Reproducibility

Mar 4, 2026cs.CY

No Certificate, No Categorical Speech Act: A Brouwerian Assertibility Constraint for Public Reason

Generative AI can convert uncertainty into authoritative-seeming verdicts, intensifying the hypersuasive force of automated speech and displacing the justificatory work on which democratic epistemic agency depends. As a corrective, I propose a Brouwer-inspired assertibility constraint for responsible AI: in high-stakes domains, systems may assert or deny claims only if they can provide a publicly inspectable and contestable certificate of entitlement; otherwise they must return Undetermined. This constraint yields a three-status interface semantics (Asserted, Denied, Undetermined) in which statuses mark entitlement to categorical speech rather than truth values of the underlying world-claim. The semantics cleanly separates internal entitlement from public standing while connecting them via the certificate as a boundary object. It also produces a time-indexed entitlement profile that is stable under numerical refinement yet revisable as the public record changes. I operationalize the constraint through decision-layer gating of threshold and argmax decisions, using internal witnesses (e.g., sound bounds or separation margins where available, and contestable surrogates otherwise) and an output contract with reason-coded abstentions. A design lemma shows that any total, certificate-sound binary interface yields witnessed decidability of the deployed predicate on its declared scope, so Undetermined is not a tunable reject option but a mandatory status whenever no adequate forcing witness is available. By making outputs answerable to challengeable warrants rather than confidence alone, the paper aims to preserve epistemic agency against the persuasive pull of automated speech in public justification.

Michael Jülich

aihorizon R&D, Munich, Germany.

Epistemology Certificates Verdict Constraint Satisfaction Reasoning Skills Surrogates