arxiv6.0 / 10

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

Houman Mehrafarin, Ioannis Konstas

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 $46\%$ to $85\%$ on LLaMA 3.1 8B (CoT: $69\%$) and from $52\%$ to $86\%$ on Qwen 2.5 7B (CoT: $77\%$), 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.

Research area

activation steeringmechanistic interpretabilityrepresentation engineering
Published
18 Nov 2026
Source
arxiv
Org
Heriot-Watt University
View paper
Sign in to read and join the discussion.