# Hidden Error Awareness in Chain-of-Thought Reasoning: The Signal Is Diagnostic, Not Causal

arXiv: https://arxiv.org/abs/2605.09502 · HTML: https://mlsanity.com/paper/2605.09502/

## Key facts

- Cited by 7 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 12 of its 16 references that are in the map.
- First posted on arXiv 10 May 2026.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)
- Mechanistic interpretability / [Steering and interpreting LLM reasoning](https://mlsanity.com/mechinterp/steering-and-interpreting-llm-reasoning/)

## Builds on (most cited first, 12 of 12)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification](https://mlsanity.com/paper/2504.05419/) (2025)

## Built on by (most cited first, 7 of 7)

- [Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model Internals](https://mlsanity.com/paper/2605.26045/) (2026)
- [Why2Speak: Faithful Reasoning for Abstaining Action Policies](https://mlsanity.com/paper/2608.20670/) (2026)
- [It's the Problem, Not the Path: Budget and Difficulty Confounds in LLM Reasoning Trajectories](https://mlsanity.com/paper/2609.03436/) (2026)
- [Hints Help But Do They Teach? Evaluating Skills Transfer in Code Generation](https://mlsanity.com/paper/2609.01106/) (2026)
- [What Visual Generators Need from Teachers: Rethinking Representation Alignment](https://mlsanity.com/paper/2609.34732/) (2026)
- [Concept Subspaces Compute Beyond the Logit Lens: A Weights-Only Test for Locating Representations Upstream of Readout](https://mlsanity.com/paper/2609.39263/) (2026)
- [From Candidate Tokens to Final Outcomes: Decoding Relative Long-Horizon Candidate Value from Reasoning Model Representations](https://mlsanity.com/paper/2610.15412/) (2026)

## Abstract (arXiv)

Chain-of-thought (CoT) prompting assumes that generated reasoning reflects a model's internal computation. We show this assumption is wrong in a specific, measurable way: models internally detect their own reasoning errors but outwardly express confidence in them. A linear probe on hidden states predicts trace correctness with 0.95 AUROC -- from the very first reasoning step (0.79) -- while verbalized confidence for wrong traces is 4.55/5, nearly identical to correct ones (4.87/5). A text-surface classifier achieves only 0.59 on the same data, confirming a 0.20-point gap invisible in the generated text. This hidden error awareness holds across three model families (Qwen, Llama, Phi), 1.5B-72B parameters, and RL-trained reasoning models (DeepSeek-R1, 0.852 AUROC). The natural question is whether this signal can fix the errors it detects. It cannot. Four interventions -- activation steering, probe-guided best-of-N, self-correction, and activation patching -- all fail; patching destroys output coherence entirely. The signal is diagnostic, not causal: a readout of computation quality, not a lever to redirect it. This delineates a boundary for mechanistic interpretability: error representations during reasoning are fundamentally different from the factual knowledge representations that prior work has successfully edited.