When Decodability Is Not Enough: Logical Validity Representations, Behavioral Dissociation, and Causal Tests in Language Models

• URL: http://arxiv.org/abs/2609.02438v1
• Date: Wed, 02 Sep 2026 11:01:09 GMT
• Title: When Decodability Is Not Enough: Logical Validity Representations, Behavioral Dissociation, and Causal Tests in Language Models
• Abstract summary: We study logical verification in five open-weight transformer models.<n>Despite near-chance behavioral performance, logical validity is often almost perfectly decodable from hidden states.<n>Our results suggest representing validity, expressing it in behavior, and using it causally are distinct.
• Score: 2.5819252531158683
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large language models can look capable of logical reasoning, but correct or incorrect answers alone tell us little about what the model represents internally. We study logical verification in five open-weight transformer models using matched valid--invalid premise--claim pairs that vary across inference families, semantic domains, templates, and difficulty levels. Despite near-chance behavioral performance, logical validity is often almost perfectly decodable from hidden states and remains strongly decodable under held-out templates, domains, and inference families. Validity also remains highly decodable on behaviorally incorrect examples in the conditions where correctness-conditioned evaluation is well defined. At the same time, exhaustive leave-one-out tests reveal clear limits to this generalization, and interventions along probe-derived validity directions have only weak, nonspecific effects compared with random controls. Our results suggest that representing validity, expressing it in behavior, and using it causally are distinct. Validity related information can be strongly decodable from a model's hidden states without being reliably expressed in its output.

Related papers

• Amplified Does Not Mean Predictive: Reasoning Behaviors in Thinking Models [56.88565331713778]
  reasoning-oriented training can make traces look more deliberative without amplifying the behaviors most tied to model correctness.<n>We quantify this mismatch with Behavioral Lift, a metric that measures how much correctness changes when a behavior is present versus absent in a model's reasoning trace.<n>We find evidence for an Amplification-Lift Gap, in which thinking models strongly amplify self-awareness, hypothesis testing, and uncertainty acknowledgment.
  arXiv  Detail & Related papers  (2026-08-13T20:37:59Z)
• The Tell-Tale Trace: Detecting Reasoning Failures in LLMs Using Chain-of-Thought Dynamics [0.9668407688201359]
  Chain-of-thought (CoT) reasoning improves large language model (LLM) performance.<n>Existing approaches that leverage verbalized CoTs to monitor reasoning correctness largely evaluate the semantic correctness or consistency of individual intermediate steps.<n>We show that capability failures can manifest as distributed, task-dependent changes in the structure of visible reasoning.
  arXiv  Detail & Related papers  (2026-08-04T08:04:36Z)
• Decodable but Not Faithful: Coupling Natural-Language Rationales to Programmatic Verifiers [0.7212939068975618]
  Language models can generate plausible rationales for their predictions, but these explanations may not faithfully represent the model's internal reasoning.<n>We propose verifier-coupled reasoning, a framework that inserts inline claims into reasoning traces and trains an auxiliary consistency head to predict programmatic verifier outputs.<n>We find a gap between decodability and faithfulness: consistency training reliably makes verifier information decodable from rationale representations, but decodability does not guarantee faithful generation.
  arXiv  Detail & Related papers  (2026-06-19T18:37:24Z)
• Evaluating Bivariate Causal Statements Based on Mutual Compatibility [7.594559816880284]
  We develop methods for evaluating causal statements over a set of $n$ variables.<n>We introduce a compatibility score that quantifies this notion of plausibility without relying on the faithfulness assumption.<n>We give theoretical and empirical evidence that both scores can successfully distinguish correct from incorrect causal statements in generic settings.
  arXiv  Detail & Related papers  (2026-05-29T19:15:09Z)
• Pando: Do Interpretability Methods Work When Models Won't Explain Themselves? [53.07826484214082]
  We introduce Pando, a model-organism benchmark that breaks this confound via an explanation axis.<n>Pando predicts held-out model decisions from $10$ labeled query-response pairs.<n>When explanations are faithful, black-box elicitation matches or exceeds all white-box methods.
  arXiv  Detail & Related papers  (2026-04-13T06:42:24Z)
• On the Identifiability of Steering Vectors in Large Language Models [0.0]
  Activation steering methods are widely used to control large language model behavior.<n>This interpretation implicitly assumes steering directions are identifiable and uniquely recoverable from input-output behavior.<n>We prove that steering vectors are fundamentally non-identifiable due to large equivalence classes of behaviorally indistinguishable interventions.
  arXiv  Detail & Related papers  (2026-02-06T15:53:50Z)
• Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification [49.506412445511934]
  Large Language Models (LLMs) show remarkable capabilities, yet their next-token prediction creates logical inconsistencies and reward hacking.<n>We introduce a formal logic verification-guided framework that dynamically interleaves formal symbolic verification with the natural language generation process.<n>We operationalize this framework via a novel two-stage training pipeline that synergizes formal logic verification-guided supervised fine-tuning and policy optimization.
  arXiv  Detail & Related papers  (2026-01-30T07:01:25Z)
• Uncovering Hidden Correctness in LLM Causal Reasoning via Symbolic Verification [56.51953062869371]
  DoVerifier is a symbolic verifier that checks whether causal expressions are derivable from a given causal graph using rules from do-calculus and probability theory.<n>Our evaluations on synthetic data and causal QA benchmarks show that DoVerifier more accurately captures semantic correctness of causal reasoning traces.
  arXiv  Detail & Related papers  (2026-01-29T03:22:58Z)
• Are Language Models Efficient Reasoners? A Perspective from Logic Programming [109.47572890883248]
  Modern language models (LMs) exhibit strong deductive reasoning capabilities, yet standard evaluations emphasize correctness while overlooking a key aspect of human-like reasoning: efficiency.<n>We propose a framework for assessing LM reasoning efficiency through the lens of logic programming.
  arXiv  Detail & Related papers  (2025-10-29T15:30:31Z)
• Rationales Are Not Silver Bullets: Measuring the Impact of Rationales on Model Performance and Reliability [70.4107059502882]
  Training language models with rationales augmentation has been shown to be beneficial in many existing works.<n>We conduct comprehensive investigations to thoroughly inspect the impact of rationales on model performance.
  arXiv  Detail & Related papers  (2025-05-30T02:39:37Z)
• Mitigating Content Effects on Reasoning in Language Models through Fine-Grained Activation Steering [14.298418197820912]
  Large language models (LLMs) frequently demonstrate reasoning limitations, often conflating content plausibility with logical validity.<n>This can result in biased inferences, where plausible arguments are incorrectly deemed logically valid or vice versa.<n>This paper investigates the problem of mitigating content biases on formal reasoning through activation steering.
  arXiv  Detail & Related papers  (2025-05-18T01:34:34Z)
• Logical Satisfiability of Counterfactuals for Faithful Explanations in NLI [60.142926537264714]
  We introduce the methodology of Faithfulness-through-Counterfactuals. It generates a counterfactual hypothesis based on the logical predicates expressed in the explanation. It then evaluates if the model's prediction on the counterfactual is consistent with that expressed logic.
  arXiv  Detail & Related papers  (2022-05-25T03:40:59Z)

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.