cs.CLNov 18, 2026

Chain-of-Thought Hidden States Reveal Task-Solving Directions for Direct Answers

Authors: Houman Mehrafarin, Ioannis Konstas

Organizations: Heriot-Watt University, Edinburgh, United Kingdom · University of Edinburgh, Edinburgh, United Kingdom

Abstract

Chain-of-Thought (CoT) prompting improves the performance of Large Language Models by eliciting intermediate reasoning steps. However, CoT is far from perfect: on some tasks, models perform worse than with direct-answer prompting, and on others they generate a few hundred tokens to reach the correct answer. We start by labelling each CoT hidden state as recovering if patching it into the direct prompt yields the correct answer, and failed otherwise. A linear probe shows that the model encodes these two classes differently. We then show that the representation space of the direct prompt holds a direction for each question that leads the model, in a short generation, to the correct answer more often than CoT does. Specifically, we rotate the direct prompt's last hidden state once, before generation, towards a direction built for each question from its own recovering and failed states. Across 25 tasks, these directions raise the direct prompt's mean accuracy from 46%46\% to 85%85\% on LLaMA 3.1 8B (CoT: 69%69\%) and from 52%52\% to 86%86\% on Qwen 2.5 7B (CoT: 77%77\%), with a tenth of CoT's tokens. CoT is thus not the shortest route to this accuracy, and these directions can be used in future work to train models to align their states with them.

Figures & tables

Appendix figures & tables11 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Apr 25, 2026

When Chain-of-Thought Fails, the Solution Hides in the Hidden States

Whether intermediate reasoning is computationally useful or merely explanatory depends on whether chain-of-thought (CoT) tokens contain task-relevant information. We present a mechanistic causal analysis of CoT on GSM8K using activation patching: transferring token-level hidden states from a CoT generation to a direct-answer run for the same question, then measuring the effect on final-answer accuracy. Across models, generating after patching yields substantially higher accuracy than both direct-answer prompting and the original CoT trace, revealing that individual CoT tokens can encode sufficient information to recover the correct answer, even when the original trace is incorrect. This task-relevant information is more prevalent in correct than incorrect CoT runs and is unevenly distributed across tokens, concentrating in mid-to-late layers and appearing earlier in the reasoning trace. Moreover, patching language tokens such as verbs and entities carry task-solving information that steers generation toward correct reasoning, whereas mathematical tokens encode answer-proximal content that rarely succeeds. Patched outputs are often shorter and yet exceed the accuracy of a full CoT trace, suggesting complete reasoning chains are not always necessary. Together, these findings demonstrate that CoT encodes recoverable, token-level problem-solving information, offering new insight into how reasoning is represented and where it breaks down.
Aug 4, 2026

Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve

Chain-of-Thought (CoT) prompting remains the standard baseline for evaluating models' reasoning abilities. Originally, this technique was introduced to elicit step-by-step reasoning from large language models (LLMs), which would otherwise tend to directly output the final answer. However, many modern LLMs produce CoT-style responses natively when presented with reasoning tasks, which made us revisit the effectiveness of standard CoT prompting. We evaluate several modern mid-sized language models on a math problem-solving task and find that models specialized for reasoning achieve better performance in a simple zero-shot setting than when using few-shot CoT examples - significantly surpassing officially reported results at no additional cost (e.g., from ∼\sim77% to ∼\sim84% for Mathstral on GSM8K). For the tested general-purpose model, a zero-shot CoT prompt is also sufficient to outperform a few-shot CoT baseline. We attribute this to a `guidance-distraction' tradeoff: standard CoT prompting also demands style adaptation, formatting compliance, and potentially undesired contextualization, which can distract models from the core reasoning task. Our findings suggest that using standard CoT prompting increasingly acts as a source of distraction as models grow stronger.
Mar 2, 2026

Post-Hoc Reasoning in Chain of Thought: Decoding and Steering Pre-Committed Answers

As chain of thought (CoT) has become central to scaling reasoning capabilities in large language models (LLMs), it has also emerged as a promising tool for interpretability, suggesting the opportunity to understand model decisions through verbalized reasoning. However, the utility of CoT toward interpretability depends upon its faithfulness---whether the model's stated reasoning reflects the underlying decision process. We provide mechanistic evidence that instruction-tuned models often determine their answer before generating CoT. Training linear probes on residual stream activations at the last token before CoT, we can predict the model's final answer with >0.9 AUC on most tasks. We find that these directions are not only predictive, but also causal: steering activations along the probe direction often flips model answers, with flip rates substantially exceeding norm-matched orthogonal baselines across most model-dataset pairs. When steering induces incorrect answers, we observe two distinct failure modes: confabulation (fabricating false premises) and non-entailment (stating correct premises but drawing unsupported conclusions). While post-hoc reasoning may be instrumentally useful when the model has a correct pre-CoT belief, these failure modes suggest it can result in undesirable behaviors when reasoning from a false belief.