Self-Anchor: Large Language Model Reasoning via Step-by-step Attention Alignment

Hongxiang Zhang, Yuan Tian, Tianyi Zhang

Keywords: Attention Steering, Reasoning, Prompting

TL;DR: A lightweight attention-steering method that structures reasoning steps, boosting LLM performance on complex tasks without retraining.

Abstract:

To solve complex reasoning tasks for Large Language Models (LLMs), prompting-based methods offer a lightweight alternative to fine-tuning and reinforcement learning.
However, as reasoning chains extend, critical intermediate steps and the original prompt will be buried in the context, receiving insufficient attention and leading to errors.
In this paper, we propose Self-Anchor, a novel pipeline that leverages the inherent structure of reasoning to steer LLM attention. Self-Anchor decomposes reasoning trajectories into structured plans and automatically aligns the model's attention to the most relevant inference steps, allowing the model to maintain focus throughout generation.
Our experiment shows that Self-Anchor outperforms SOTA prompting methods across six benchmarks.
Notably, Self-Anchor significantly reduces the performance gap between ``non-reasoning'' models and specialized reasoning models, with the potential to enable most LLMs to tackle complex reasoning tasks without retraining.

Primary Area: causal reasoning

Submission Number: 326