Skip to content
Preprint

Reasoning Consistency Scanning: A Framework for Auditing Chain-of-Thought Validity in AI Safety Evaluations

Jul 2026 · 0 citations · 15 references
Computer Science

TL;DR

This work formalizes reasoning consistency as distinct from faithfulness and defines a six-subtype taxonomy of inconsistency, showing that reasoning inconsistency is present, detectable, and varies systematically across both models and task types.

Abstract

Prior work has shown that chain-of-thought (CoT) reasoning is often unfaithful: a model's stated reasoning does not reliably reflect the process that produced its output. Detecting unfaithfulness, though, requires controlled experimental interventions, which cannot be applied to evaluation transcripts after the fact. We turn instead to a more tractable question that has received less attention: whether the stated reasoning is logically consistent with the answer it accompanies. Unlike faithfulness, consistency can be assessed from a transcript alone, with no intervention. We introduce reasoning consistency scanning, a reusable method for detecting this property in AI safety evaluation transcripts. Our contributions are fourfold. First, we formalize reasoning consistency as distinct from faithfulness and define a six-subtype taxonomy of inconsistency. Second, we build a validated benchmark of 60 transcripts, manually adapted from InstrumentalEval outputs. Third, we implement a working scanner for InspectScout, the first to target this property in safety evaluation transcripts. Fourth, we report results across four generator models and three evaluations from inspect_evals, showing that reasoning inconsistency is present, detectable, and varies systematically across both models and task types.

View source

Similar papers

Preprint Jul 2026

A Reference-Free Score for Detecting Silent Reasoning Failures in Large Language Models

The Reasoning Answer Faithfulness Score (RAFS) is introduced, a reference free, instance level diagnostic of whether an emitted mathematical trace is locally credible, supports its answer, and is stable under resampling and targeted counterfactual interventions.

Vivek Shukla, Varun Shukla, Atul et al. · 0 citations
Preprint Aug 2026

The Tell-Tale Trace: Detecting Reasoning Failures in LLMs Using Chain-of-Thought Dynamics

Results show that capability failures can manifest as distributed, task-dependent changes in the structure of visible reasoning, and that CoT dynamics agnostic to whether the verbalized trace reflects the model's internal computations can help diagnose and correct failures.

Shashwat Sourav, Aishwarya H. Balwani · 0 citations
Preprint Aug 2026

TRACES: A Benchmark for Epistemic Reliability in Scientific Reasoning by LLMs

A probe corpus of 42 retracted, fraudulent, and pseudoscientific papers is paired with a methodology for eliciting and scoring single-shot model engagement with each paper's framing, indicating an urgent need for guardrail infrastructure for scientific deployment of language models.

V. Rodionov, Shamil Assylbekov · 0 citations
Preprint Jul 2026

Interventional Grounding Audits: Black-Box Premise-Dependency Tests for LLM Chain-of-Thought via Predicate Substitution

This work introduces interventional grounding audits, a black-box, step-level test of premise dependency, and identifies that 66% of correctly-solved problems contain at least one aligned step insensitive to a direct proof-tree dependency under consistent substitution.

H. Nakamura · 0 citations
Review Aug 2026

No Judgment Without a Reason: Counterfactual Receipts for Versioned AI Evaluators

Evaluators often produce correct labels via flawed reasoning, a critical failure for agentic systems gating actions, routing reviews, or supplying training feedback. Standard evaluation only verifies final label correctness, ignoring whether judgment changes stem from valid evidence, consistent rules, or proper rule applicability. We formalize evaluator reasoning accountability via three core sources: grounds, norms, and authority. Varying these sources yields an eight-cell counterfactual judgment cube to characterize judgment updates. We define judgment receipts as minimal source replacement sets that reproduce revised verdicts to explain judgment transitions. We derive certification cost bounds for black-box evaluators and present ReasonBench, a policy and logical reasoning benchmark with verifiable receipts covering 19,520 cases and 7,200 controls. In frozen evaluations, Qwen3-1.7B reaches 98.41% receipt accuracy, while cube prediction scores 96.99%, a consistent 1.42-point drop validated by Qwen3-0.6B replication. Strong standard accuracy masks severe robustness flaws. Meaning-preserving source permutations reduce valid receipt recovery to 54.8% and 49.2% for direct and cube prediction. Models trained on simple single-source changes retain 93.75% verdict accuracy but recover only 7.16% of receipts for complex multi-source updates. Permutation retraining boosts consistency to 96.6% yet worsens cube prediction deficits. Structured counterfactual supervision fails to guarantee robust reasoning. We show reason-aware evaluation must decouple prediction and certification, reporting transformation consistency alongside standard accuracy for trustworthy evaluator auditing.

Yefei Chen, Weining Zhang · 0 citations