# Is Chain-of-Thought Really Not Explainability? Chain-of-Thought Can Be Faithful without Hint Verbalization

arXiv: https://arxiv.org/abs/2512.23032 · HTML: https://mlsanity.com/paper/2512.23032/

## Key facts

- Cited by 16 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 6 of its 45 references that are in the map.
- First posted on arXiv 28 Dec 2025.

## 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, 6 of 6)

- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP](https://mlsanity.com/paper/2212.14024/) (2022)
- [AI Control: Improving Safety Despite Intentional Subversion](https://mlsanity.com/paper/2312.06942/) (2023)
- [Chain-of-Thought Reasoning In The Wild Is Not Always Faithful](https://mlsanity.com/paper/2503.08679/) (2025)
- [Agentic Misalignment: How LLMs Could Be Insider Threats](https://mlsanity.com/paper/2510.05179/) (2025)

## Built on by (most cited first, 16 of 16)

- [RAGEN-2: Reasoning Collapse in Agentic RL](https://mlsanity.com/paper/2604.06268/) (2026)
- [Counterfactual Simulation Training for Chain-of-Thought Faithfulness](https://mlsanity.com/paper/2602.20710/) (2026)
- [Lie to Me: How Faithful Is Chain-of-Thought Reasoning in Reasoning Models?](https://mlsanity.com/paper/2603.22582/) (2026)
- [Measuring Faithfulness Depends on How You Measure: Classifier Sensitivity in LLM Chain-of-Thought Evaluation](https://mlsanity.com/paper/2603.20172/) (2026)
- [When Shallow Wins: Silent Failures and the Depth-Accuracy Paradox in Latent Reasoning](https://mlsanity.com/paper/2603.03475/) (2026)
- [Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth](https://mlsanity.com/paper/2605.25052/) (2026)
- [Investigating the Interplay between Contextual and Parametric Chain-of-Thought Faithfulness under Optimization](https://mlsanity.com/paper/2605.24960/) (2026)
- [Measuring AI Reasoning: A Guide for Researchers](https://mlsanity.com/paper/2605.02442/) (2026)
- [Local Causal Attribution of Chain-of-Thought Reasoning](https://mlsanity.com/paper/2606.21821/) (2026)
- [Two Regimes of Chain-of-Thought Unfaithfulness: Metric-Based Detection Fails Where Models Are Wrong](https://mlsanity.com/paper/2607.23458/) (2026)
- [Mechanistic Interpretability of Chain-of-Thought Reasoning via Sequential Activation Patching](https://mlsanity.com/paper/2608.22332/) (2026)
- [Chain-of-Thought Faithfulness of Reasoning Models Varies with Where and How Preference Cues Are Delivered](https://mlsanity.com/paper/2608.29464/) (2026)
- [LLM Reasoning Is Latent, Not the Chain of Thought](https://mlsanity.com/paper/2604.15726/) (2026)
- [Risky Business: Measuring The Faithfulness-Safety Tension](https://mlsanity.com/paper/2608.03745/) (2026)
- [Untangling the Mechanisms of Misleading Context in Medical Question Answering](https://mlsanity.com/paper/2609.02754/) (2026)
- [Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment](https://mlsanity.com/paper/2609.38972/) (2026)

## Abstract (arXiv)

Recent work, using the Biasing Features metric, labels a CoT as unfaithful if it omits a prompt-injected hint that affected the prediction. We argue this metric adopts a narrow notion of faithfulness and confuses unfaithfulness with incompleteness, the lossy compression needed to turn distributed transformer computation into a linear natural language narrative. On multi-hop reasoning tasks with instruct-tuned and reasoning models, many CoTs flagged as unfaithful by Biasing Features are judged faithful by other metrics, exceeding 50% in some models. With a new faithful@k metric, we show that larger inference-time budgets greatly increase hint verbalization (up to 90% in some settings), suggesting much apparent unfaithfulness is due to tight token limits. Using Causal Mediation Analysis, we further show that even non-verbalized hints can causally mediate prediction changes through the CoT. We therefore caution against relying solely on hint-based evaluations and advocate a broader interpretability toolkit, including causal mediation and corruption-based metrics. We do not claim all CoTs are faithful, only that the absence of hint words alone does not prove unfaithfulness.