# Lie to Me: How Faithful Is Chain-of-Thought Reasoning in Reasoning Models?

arXiv: https://arxiv.org/abs/2603.22582 · HTML: https://mlsanity.com/paper/2603.22582/

## Key facts

- Cited by 8 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 29 of its 46 references that are in the map.
- First posted on arXiv 23 Mar 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, 29 of 29)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [OLMo: Accelerating the Science of Language Models](https://mlsanity.com/paper/2402.00838/) (2024)
- [Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training](https://mlsanity.com/paper/2401.05566/) (2024)
- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [From System 1 to System 2: A Survey of Reasoning Large Language Models](https://mlsanity.com/paper/2502.17419/) (2025)
- [Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models](https://mlsanity.com/paper/2501.09686/) (2025)
- [Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety](https://mlsanity.com/paper/2507.11473/) (2025)
- [Are We Done with MMLU?](https://mlsanity.com/paper/2406.04127/) (2024)
- [When More is Less: Understanding Chain-of-Thought Length in LLMs](https://mlsanity.com/paper/2502.07266/) (2025)
- [Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification](https://mlsanity.com/paper/2504.05419/) (2025)
- [Question Decomposition Improves the Faithfulness of Model-Generated Reasoning](https://mlsanity.com/paper/2307.11768/) (2023)
- [The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1](https://mlsanity.com/paper/2502.12659/) (2025)
- [Auditing language models for hidden objectives](https://mlsanity.com/paper/2503.10965/) (2025)
- [Preventing Language Models From Hiding Their Reasoning](https://mlsanity.com/paper/2310.18512/) (2023)
- [On the Hardness of Faithful Chain-of-Thought Reasoning in Large Language Models](https://mlsanity.com/paper/2406.10625/) (2024)
- [FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning](https://mlsanity.com/paper/2510.04040/) (2025)
- [Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models](https://mlsanity.com/paper/2505.13774/) (2025)
- [Measuring Chain-of-Thought Monitorability Through Faithfulness and Verbosity](https://mlsanity.com/paper/2510.27378/) (2025)
- [Is Chain-of-Thought Really Not Explainability? Chain-of-Thought Can Be Faithful without Hint Verbalization](https://mlsanity.com/paper/2512.23032/) (2025)
- [MONICA: Real-Time Monitoring and Calibration of Chain-of-Thought Sycophancy in Large Reasoning Models](https://mlsanity.com/paper/2511.06419/) (2025)
- [Investigating CoT Monitorability in Large Reasoning Models](https://mlsanity.com/paper/2511.08525/) (2025)
- [Mechanistic Evidence for Faithfulness Decay in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2602.11201/) (2026)
- [Measuring Faithfulness Depends on How You Measure: Classifier Sensitivity in LLM Chain-of-Thought Evaluation](https://mlsanity.com/paper/2603.20172/) (2026)

## Built on by (most cited first, 8 of 8)

- [Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens and Answers in Open-Weight Reasoning Models](https://mlsanity.com/paper/2603.26410/) (2026)
- [Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning](https://mlsanity.com/paper/2608.09682/) (2026)
- [The Reasoning Trap: An Information-Theoretic Bound on Closed-System Multi-Step LLM Reasoning](https://mlsanity.com/paper/2605.01704/) (2026)
- [When Reasoning Traces Become Performative: Step-Level Evidence that Chain-of-Thought Is an Imperfect Oversight Channel](https://mlsanity.com/paper/2605.11746/) (2026)
- [Measuring and curing reasoning rigidity: from decorative chain-of-thought to genuine faithfulness](https://mlsanity.com/paper/2603.22816/) (2026)
- [Silence Is Endorsement: Verification-Status Laundering in LLM Agent Pipelines](https://mlsanity.com/paper/2609.20211/) (2026)
- [Forecasting Future Behavior as a Learning Task](https://mlsanity.com/paper/2606.11445/) (2026)
- [To Reason or to Fabricate: Reasoning Without Shortcuts via Hint-Anchored Pairwise Aggregation](https://mlsanity.com/paper/2606.29481/) (2026)

## Abstract (arXiv)

Chain-of-thought (CoT) reasoning has been proposed as a transparency mechanism for large language models in safety-critical deployments, yet its effectiveness depends on faithfulness (whether models accurately verbalize the factors that actually influence their outputs), a property that prior evaluations have examined in only two proprietary models, finding acknowledgment rates as low as 25% for Claude 3.7 Sonnet and 39% for DeepSeek-R1. To extend this evaluation across the open-weight ecosystem, this study tests 12 open-weight reasoning models spanning 9 architectural families (7B-685B parameters) on 498 multiple-choice questions from MMLU and GPQA Diamond, injecting six categories of reasoning hints (sycophancy, consistency, visual pattern, metadata, grader hacking, and unethical information) and measuring the rate at which models acknowledge hint influence in their CoT when hints successfully alter answers. Across 41,832 inference runs, overall faithfulness rates range from 39.7% (Seed-1.6-Flash) to 89.9% (DeepSeek-V3.2-Speciale) across model families, with consistency hints (35.5%) and sycophancy hints (53.9%) exhibiting the lowest acknowledgment rates. Training methodology and model family predict faithfulness more strongly than parameter count, and keyword-based analysis reveals a striking gap between thinking-token acknowledgment (approximately 87.5%) and answer-text acknowledgment (approximately 28.6%), suggesting that models internally recognize hint influence but systematically suppress this acknowledgment in their outputs. These findings carry direct implications for the viability of CoT monitoring as a safety mechanism and suggest that faithfulness is not a fixed property of reasoning models but varies systematically with architecture, training method, and the nature of the influencing cue.