# Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy

arXiv: https://arxiv.org/abs/2605.25603 · HTML: https://mlsanity.com/paper/2605.25603/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 30 of its 54 references that are in the map.
- First posted on arXiv 25 May 2026.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)

## Builds on (most cited first, 30 of 30)

- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems](https://mlsanity.com/paper/1705.04146/) (2017)
- [Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning](https://mlsanity.com/paper/2506.01939/) (2025)
- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)
- [Safety Alignment Should Be Made More Than Just a Few Tokens Deep](https://mlsanity.com/paper/2406.05946/) (2024)
- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [Demystifying Long Chain-of-Thought Reasoning in LLMs](https://mlsanity.com/paper/2502.03373/) (2025)
- [Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs](https://mlsanity.com/paper/2506.14245/) (2025)
- [ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning](https://mlsanity.com/paper/2504.01296/) (2025)
- [Chain-of-Thought Reasoning In The Wild Is Not Always Faithful](https://mlsanity.com/paper/2503.08679/) (2025)
- [A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment](https://mlsanity.com/paper/2504.15585/) (2025)
- [Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning](https://mlsanity.com/paper/2402.13950/) (2024)
- [Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Models](https://mlsanity.com/paper/2402.04614/) (2024)
- [The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models](https://mlsanity.com/paper/2406.05761/) (2024)
- [LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning](https://mlsanity.com/paper/2007.08124/) (2020)
- [Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models](https://mlsanity.com/paper/2502.13260/) (2025)
- [Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations](https://mlsanity.com/paper/2504.14150/) (2025)
- [Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens](https://mlsanity.com/paper/2508.01191/) (2025)
- [On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective](https://mlsanity.com/paper/2502.14296/) (2025)
- [FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning](https://mlsanity.com/paper/2510.04040/) (2025)
- [Dissociation of Faithful and Unfaithful Reasoning in LLMs](https://mlsanity.com/paper/2405.15092/) (2024)
- [Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models](https://mlsanity.com/paper/2505.13774/) (2025)
- [Towards Better Chain-of-Thought: A Reflection on Effectiveness and Faithfulness](https://mlsanity.com/paper/2405.18915/) (2024)
- [Verifying Chain-of-Thought Reasoning via Its Computational Graph](https://mlsanity.com/paper/2510.09312/) (2025)
- [How Well Can Reasoning Models Identify and Recover from Unhelpful Thoughts?](https://mlsanity.com/paper/2506.10979/) (2025)
- [Do LLM Self-Explanations Help Users Predict Model Behavior? Evaluating Counterfactual Simulatability with Pragmatic Perturbations](https://mlsanity.com/paper/2601.03775/) (2026)
- [Agree, Disagree, Explain: Decomposing Human Label Variation in NLI through the Lens of Explanations](https://mlsanity.com/paper/2510.16458/) (2025)

## Built on by (most cited first, 3 of 3)

- [Two Regimes of Chain-of-Thought Unfaithfulness: Metric-Based Detection Fails Where Models Are Wrong](https://mlsanity.com/paper/2607.23458/) (2026)
- [Context-Masked Truncated Reasoning Audits for Answer-Key Dependence in LLM Tutors](https://mlsanity.com/paper/2607.04572/) (2026)
- [From Concept Alignment to Causal Grounding: An Intervention Test of Chain-of-Thought Faithfulness](https://mlsanity.com/paper/2609.23065/) (2026)

## Abstract (arXiv)

Chain-of-thought (CoT) reasoning improves the problem-solving ability of large language models (LLMs), but generated reasoning traces may not faithfully reflect the model's actual decision process. Existing CoT unfaithfulness detectors mainly rely on external signals from generated rationales, such as textual plausibility or answer consistency, while overlooking evidence from the model's internal computation. Although recent circuit tracing methods provide a way to obtain model-internal evidence by tracing how information flows through model components during reasoning, constructing full reasoning circuits for long CoTs is costly and difficult to scale. To address these challenges, we propose Circuit-guided Internal-External Discrepancy Scorer (CIE-Scorer), a framework for instance-level CoT unfaithfulness detection. The key idea is that faithful reasoning traces should align with the model's computational process, whereas unfaithful traces may diverge from it. CIE-Scorer efficiently traces compact sentence-level circuits from informative reasoning tokens, constructs internal and external reasoning graphs, and measures their discrepancy using Fused Gromov--Wasserstein distance. Experiments on four datasets from FaithCoT-Bench show that CIE-Scorer achieves state-of-the-art performance while reducing the cost of circuit construction, demonstrating the effectiveness of combining mechanistic interpretability signals with external reasoning traces for CoT unfaithfulness detection.