Reasoning Consistency Scanning: A Framework for Auditing Chain-of-Thought Validity in AI Safety Evaluations
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 faithfulne
Record details
Published: 8 July 2026
Source: arXiv
Category: Research
Topics: Safety & alignment · Transparency
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Trustworthy Machine Learning through the Lens of Combinatorial Optimization: Survey and Research Perspectives
arXiv fairness query · 8 July 2026
X-FEMR: A Token-level Explainable Approach for Electronic Health Records Foundation Models using Transformer-based Models
arXiv · 7 July 2026
The interpretability paradox in cancer imaging and risk prediction: a critical narrative review of explainable AI, failure modes, and design alternatives
Artificial Intelligence Review · 7 July 2026
ANCHOR: Automated Alignment Auditing for CLI Agents on Real-World Harm
arXiv · 11 July 2026
Explainable Reinforcement Learning for Adaptive Traffic Signal Control
arXiv · 4 July 2026
Auditing the Risk Claims of Distributional Reinforcement Learning
arXiv cs.AI · 13 July 2026
How to cite this record
ethics.ai (8 July 2026), “Reasoning Consistency Scanning: A Framework for Auditing Chain-of-Thought Validity in AI Safety Evaluations,” evidence record 131, https://ethics.ai/record/131 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.