Attn-GS: Attention-Guided Context Compression for Efficient Personalized LLMs

TL;DR

This paper introduces Attn-GS, a novel attention-guided framework that leverages LLMs' attention patterns to effectively compress user profiles, enabling efficient personalization with minimal token usage and high performance.

Contribution

It proposes a new method utilizing attention feedback for context compression, improving personalization efficiency without sacrificing accuracy.

Findings

Attn-GS reduces token usage by 50 times.

It outperforms baseline methods across multiple tasks.

Performance approaches that of using full context.

Abstract

Personalizing large language models (LLMs) to individual users requires incorporating extensive interaction histories and profiles, but input token constraints make this impractical due to high inference latency and API costs. Existing approaches rely on heuristic methods such as selecting recent interactions or prompting summarization models to compress user profiles. However, these methods treat context as a monolithic whole and fail to consider how LLMs internally process and prioritize different profile components. We investigate whether LLMs' attention patterns can effectively identify important personalization signals for intelligent context compression. Through preliminary studies on representative personalization tasks, we discover that (a) LLMs' attention patterns naturally reveal important signals, and (b) fine-tuning enhances LLMs' ability to distinguish between relevant and irrelevant information. Based on these insights, we propose Attn-GS, an attention-guided context compression framework that leverages attention feedback from a marking model to mark important personalization sentences, then guides a compression model to generate task-relevant, high-quality compressed user contexts. Extensive experiments demonstrate that Attn-GS significantly outperforms various baselines across different tasks, token limits, and settings, achieving performance close to using full context while reducing token usage by 50 times.