When Verification Fails: How Compositionally Infeasible Claims Escape Rejection

• URL: http://arxiv.org/abs/2604.10990v1
• Date: Mon, 13 Apr 2026 04:48:20 GMT
• Title: When Verification Fails: How Compositionally Infeasible Claims Escape Rejection
• Abstract summary: We show that existing verification benchmarks cannot distinguish between rigorous claim verification and simple salient-constraint reliance.<n>We construct compositionally infeasible claims where the salient constraint is supported but a non-salient constraint is contradicted.<n>We show that different models occupy distinct positions on a shared ROC curve, indicating that the gap between model families reflects differences in verification threshold rather than underlying reasoning ability.
• Score: 30.404615085122046
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Scientific claim verification, the task of determining whether claims are entailed by scientific evidence, is fundamental to establishing discoveries in evidence while preventing misinformation. This process involves evaluating each asserted constraint against validated evidence. Under the Closed-World Assumption (CWA), a claim is accepted if and only if all asserted constraints are positively supported. We show that existing verification benchmarks cannot distinguish models enforcing this standard from models applying a simpler shortcut called salient-constraint checking, which applies CWA's rejection criterion only to the most salient constraint and accepts when that constraint is supported. Because existing benchmarks construct infeasible claims by perturbing a single salient element they are insufficient at distinguishing between rigorous claim verification and simple salient-constraint reliance. To separate the two, we construct compositionally infeasible claims where the salient constraint is supported but a non-salient constraint is contradicted. Across model families and modalities, models that otherwise saturate existing benchmarks consistently over-accept these claims, confirming the prevalence of such shortcut reasoning. Via model context interventions, we show that different models and prompting strategies occupy distinct positions on a shared ROC curve, indicating that the gap between model families reflects differences in verification threshold rather than underlying reasoning ability, and that the compositional inference bottleneck is a structural property of current verification behavior that strategy guidance alone cannot overcome.

Related papers

• CLAIM: Leading Open-domain Active Clarification of Large Language Models with Uncertainty Measurement [50.91045324738942]
  CLAIM is an uncertainty-driven framework for active clarification learning in open-domain settings.<n>We propose an entropy-driven synthetic data generation pipeline that integrates uncertainty estimation with semantic clustering and reasoning-based judgments.<n> Experimental results demonstrate that CLAIM can learn stable and generalizable clarification strategies without relying on manually labeled data.
  arXiv  Detail & Related papers  (2026-08-12T04:27:45Z)
• Position: Anthropomorphic Misalignment Research Needs Stronger Evidence [52.76826423649968]
  We show how conceptual ambiguity, non-robust datasets, experimental design, and insufficient causal interventions can lead to overinterpretation of model behaviors.<n>This position paper aims to offer guidance on evidentiary considerations that can help improve methodological rigor in AMR.
  arXiv  Detail & Related papers  (2026-05-29T16:38:53Z)
• Causal Discovery as Dialectical Aggregation: A Quantitative Argumentation Framework [13.587507786613664]
  Constraint-based causal discovery is brittle in finite-sample regimes.<n>We propose Quantitative Argumentation for Causal Discovery (QACD)<n>QACD represents CI outcomes as graded, defeasible arguments rather than irreversible constraints.
  arXiv  Detail & Related papers  (2026-04-26T09:47:41Z)
• Preregistered Belief Revision Contracts [2.28438857884398]
  We introduce PBRC (Preregistered Belief Revision Contracts), a protocol-level mechanism that separates open communication from admissible change.<n>A PBRC contract publicly fixes first-order evidence triggers, admissible revision operators, a priority rule, and a fallback policy.<n>We show that auditable trigger protocols admit evidential PBRC normal forms that preserve belief trajectories and canonicalized audit traces.
  arXiv  Detail & Related papers  (2026-04-16T22:22:54Z)
• Causality is Key for Interpretability Claims to Generalise [35.833847356014154]
  Interpretability research on large language models (LLMs) has yielded important insights into model behaviour.<n> recurring pitfalls persist: findings that do not generalise, and causal interpretations that outrun the evidence.<n>Pearl's causal hierarchy clarifies what an interpretability study can justify.
  arXiv  Detail & Related papers  (2026-02-18T18:45:04Z)
• Retrieve-Refine-Calibrate: A Framework for Complex Claim Fact-Checking [32.6738019397553]
  We propose a Retrieve-Refine-Calibrate (RRC) framework based on large language models (LLMs)<n>Specifically, the framework first identifies the entities mentioned in the claim and retrieves evidence relevant to them.<n>Then, it refines the retrieved evidence based on the claim to reduce irrelevant information.<n>Finally, it calibrates the verification process by re-evaluating low-confidence predictions.
  arXiv  Detail & Related papers  (2026-01-23T08:48:52Z)
• Feasibility Preservation under Monotone Retrieval Truncation [0.12183405753834557]
  We study retrieval from a structural perspective, modeling query answering as a feasibility problem under truncation.<n>We show that monotone truncation suffices to guarantee finite witnessability for individual queries.<n>We further exhibit sharp counterexamples demonstrating failure under non-monotone truncation, non-finitely-generated query classes, and purely slotwise coverage.
  arXiv  Detail & Related papers  (2026-01-21T18:25:16Z)
• Eidoku: A Neuro-Symbolic Verification Gate for LLM Reasoning via Structural Constraint Satisfaction [0.0]
  Large Language Models (LLMs) frequently produce hallucinated statements that are assigned high likelihood by the model itself.<n>This suggests that hallucination is often not a low-confidence phenomenon, but a failure of structural consistency.<n>We reformulate the verification of LLM reasoning as a Constraint Satisfaction Problem (CSP) operating independently of the generation likelihood.
  arXiv  Detail & Related papers  (2025-12-19T05:29:43Z)
• COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees [51.5976496056012]
  COIN is an uncertainty-guarding selection framework that calibrates statistically valid thresholds to filter a single generated answer per question.<n>COIN estimates the empirical error rate on a calibration set and applies confidence interval methods to establish a high-probability upper bound on the true error rate.<n>We demonstrate COIN's robustness in risk control, strong test-time power in retaining admissible answers, and predictive efficiency under limited calibration data.
  arXiv  Detail & Related papers  (2025-06-25T07:04:49Z)
• Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization [58.390885294401066]
  Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs)<n>RAG pipelines often fail to ensure that model reasoning remains consistent with the evidence retrieved, leading to factual inconsistencies or unsupported conclusions.<n>We propose AlignRAG, a novel iterative framework grounded in Critique-Driven Alignment (CDA)<n>We introduce AlignRAG-auto, an autonomous variant that dynamically terminates refinement, removing the need to pre-specify the number of critique iterations.
  arXiv  Detail & Related papers  (2025-04-21T04:56:47Z)
• TrustLoRA: Low-Rank Adaptation for Failure Detection under Out-of-distribution Data [62.22804234013273]
  We propose a simple failure detection framework to unify and facilitate classification with rejection under both covariate and semantic shifts.<n>Our key insight is that by separating and consolidating failure-specific reliability knowledge with low-rank adapters, we can enhance the failure detection ability effectively and flexibly.
  arXiv  Detail & Related papers  (2025-04-20T09:20:55Z)
• When Does Confidence-Based Cascade Deferral Suffice? [69.28314307469381]
  Cascades are a classical strategy to enable inference cost to vary adaptively across samples. A deferral rule determines whether to invoke the next classifier in the sequence, or to terminate prediction. Despite being oblivious to the structure of the cascade, confidence-based deferral often works remarkably well in practice.
  arXiv  Detail & Related papers  (2023-07-06T04:13:57Z)
• Representation Disentaglement via Regularization by Causal Identification [3.9160947065896803]
  We propose the use of a causal collider structured model to describe the underlying data generative process assumptions in disentangled representation learning. For this, we propose regularization by identification (ReI), a modular regularization engine designed to align the behavior of large scale generative models with the disentanglement constraints imposed by causal identification.
  arXiv  Detail & Related papers  (2023-02-28T23:18:54Z)
• Structural Causal Models Are (Solvable by) Credal Networks [70.45873402967297]
  Causal inferences can be obtained by standard algorithms for the updating of credal nets. This contribution should be regarded as a systematic approach to represent structural causal models by credal networks. Experiments show that approximate algorithms for credal networks can immediately be used to do causal inference in real-size problems.
  arXiv  Detail & Related papers  (2020-08-02T11:19:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.