# Reasoning Models Will Sometimes Lie About Their Reasoning

arXiv: https://arxiv.org/abs/2601.07663 · HTML: https://mlsanity.com/paper/2601.07663/

## Key facts

- Cited by 6 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 25 of its 33 references that are in the map.
- First posted on arXiv 12 Jan 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, 25 of 25)

- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [Faithful Chain-of-Thought Reasoning](https://mlsanity.com/paper/2301.13379/) (2023)
- [Defending Against Indirect Prompt Injection Attacks With Spotlighting](https://mlsanity.com/paper/2403.14720/) (2024)
- [Do Large Language Models Know What They Don't Know?](https://mlsanity.com/paper/2305.18153/) (2023)
- [Chain-of-Thought Reasoning In The Wild Is Not Always Faithful](https://mlsanity.com/paper/2503.08679/) (2025)
- [Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning](https://mlsanity.com/paper/2402.13950/) (2024)
- [PromptArmor: Simple yet Effective Prompt Injection Defenses](https://mlsanity.com/paper/2507.15219/) (2025)
- [ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases](https://mlsanity.com/paper/2510.20270/) (2025)
- [Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps](https://mlsanity.com/paper/2502.14829/) (2025)
- [On the Hardness of Faithful Chain-of-Thought Reasoning in Large Language Models](https://mlsanity.com/paper/2406.10625/) (2024)
- [Teaching Large Language Models to Express Knowledge Boundary from Their Own Signals](https://mlsanity.com/paper/2406.10881/) (2024)
- [LogiCoT: Logical Chain-of-Thought Instruction-Tuning](https://mlsanity.com/paper/2305.12147/) (2023)
- [FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning](https://mlsanity.com/paper/2510.04040/) (2025)
- [BeHonest: Benchmarking Honesty in Large Language Models](https://mlsanity.com/paper/2406.13261/) (2024)
- [A Survey on the Honesty of Large Language Models](https://mlsanity.com/paper/2409.18786/) (2024)
- [ReasonIF: Large Reasoning Models Fail to Follow Instructions During Reasoning](https://mlsanity.com/paper/2510.15211/) (2025)
- [Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning](https://mlsanity.com/paper/2510.04081/) (2025)

## Built on by (most cited first, 6 of 6)

- [Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values](https://mlsanity.com/paper/2607.14345/) (2026)
- [Quantifying Faithful Confidence Expression in Large Reasoning Models](https://mlsanity.com/paper/2606.03969/) (2026)
- [Seeing the Reasoning: How LLM Rationales Influence User Trust and Decision-Making in Factual Verification Tasks](https://mlsanity.com/paper/2603.07306/) (2026)
- [Can Reasoning Models Detect Changes to their Chains of Thought?](https://mlsanity.com/paper/2606.22085/) (2026)
- [Reasoning Consistency Scanning: A Framework for Auditing Chain-of-Thought Validity in AI Safety Evaluations](https://mlsanity.com/paper/2607.07229/) (2026)
- [Risky Business: Measuring The Faithfulness-Safety Tension](https://mlsanity.com/paper/2608.03745/) (2026)

## Abstract (arXiv)

Hint-based faithfulness evaluations have established that Large Reasoning Models (LRMs) may not say what they think: they do not always volunteer information about how key parts of the input (e.g. answer hints) influence their reasoning. Yet, these evaluations also fail to specify what models should do when confronted with hints or other unusual prompt content -- even though versions of such instructions are standard security measures (e.g. for countering prompt injections). Here, we study faithfulness under this more realistic setting in which models are explicitly alerted to the possibility of unusual inputs. We find that such instructions can yield strong results on faithfulness metrics from prior work. However, results on new, more granular metrics proposed in this work paint a mixed picture: although models may acknowledge the presence of hints, they will often deny intending to use them -- even when permitted to use hints and even when it can be demonstrated that they are using them. Our results thus raise broader challenges for CoT monitoring and interpretability.