ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models

ACL ARR 2025 May Submission2716 Authors

Abstract: Recent studies have shown that Large Language Models (LLMs) augmented with chain-of-thought (CoT) reasoning demonstrate impressive problem-solving abilities. However, in this work, we identify a recurring issue where these models occasionally generate overly short reasoning, leading to degraded performance on even simple mathematical problems. Specifically, we investigate how reasoning length is embedded in the hidden representations of reasoning models and its impact on accuracy. Our analysis reveals that reasoning length is governed by a linear direction in the representation space, allowing us to induce overly short reasoning by steering the model along this direction. Building on this insight, we introduce ThinkEdit, a simple yet effective weight-editing approach to mitigate the issue of overly short reasoning. We first identify a small subset of attention heads (approximately 4\%) that predominantly drive short reasoning behavior. We then edit the output projection weights of these heads to remove the short reasoning direction. With changes to only 0.2\% of the model's parameters, ThinkEdit effectively reduces overly short reasoning and yields notable accuracy gains for short reasoning outputs (+6.39\%), along with an overall improvement across multiple math benchmarks (+3.34\%). Our findings provide new mechanistic insights into how reasoning length is controlled within LLMs and highlight the potential of fine-grained model interventions to improve reasoning quality.

Paper Type: Long

Research Area: Interpretability and Analysis of Models for NLP

Research Area Keywords: model editing, probing, robustness

Contribution Types: Model analysis & interpretability

Languages Studied: English

Submission Number: 2716