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

arXiv: https://arxiv.org/abs/2602.07778 · HTML: https://mlsanity.com/paper/2602.07778/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Prompt and context compression, one of 12 directions in Efficient LLM inference and serving.
- Builds on 20 of its 33 references that are in the map.
- First posted on arXiv 8 Feb 2026.

## Placed in

- Efficient LLM inference and serving / [Prompt and context compression](https://mlsanity.com/inference/prompt-and-context-compression/)

## Builds on (most cited first, 20 of 20)

- [SnapKV: LLM Knows What You are Looking for Before Generation](https://mlsanity.com/paper/2404.14469/) (2024)
- [LaMP: When Large Language Models Meet Personalization](https://mlsanity.com/paper/2304.11406/) (2023)
- [Is ChatGPT a Good Recommender? A Preliminary Study](https://mlsanity.com/paper/2304.10149/) (2023)
- [Large Language Models for Education: A Survey and Outlook](https://mlsanity.com/paper/2403.18105/) (2024)
- [Personality Traits in Large Language Models](https://mlsanity.com/paper/2307.00184/) (2023)
- [Uncovering ChatGPT's Capabilities in Recommender Systems](https://mlsanity.com/paper/2305.02182/) (2023)
- [The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)](https://mlsanity.com/paper/2402.16893/) (2024)
- [User Behavior Simulation with Large Language Model based Agents](https://mlsanity.com/paper/2306.02552/) (2023)
- [AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systems](https://mlsanity.com/paper/2310.09233/) (2023)
- [PALR: Personalization Aware LLMs for Recommendation](https://mlsanity.com/paper/2305.07622/) (2023)
- [Overthinking the Truth: Understanding how Language Models Process False Demonstrations](https://mlsanity.com/paper/2307.09476/) (2023)
- [Successor Heads: Recurring, Interpretable Attention Heads In The Wild](https://mlsanity.com/paper/2312.09230/) (2023)
- [In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation](https://mlsanity.com/paper/2403.01548/) (2024)
- [PersonaX: A Recommendation Agent Oriented User Modeling Framework for Long Behavior Sequence](https://mlsanity.com/paper/2503.02398/) (2025)
- [Cognitive Personalized Search Integrating Large Language Models with an Efficient Memory Mechanism](https://mlsanity.com/paper/2402.10548/) (2024)
- [GMSA: Enhancing Context Compression via Group Merging and Layer Semantic Alignment](https://mlsanity.com/paper/2505.12215/) (2025)
- [Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective](https://mlsanity.com/paper/2411.14572/) (2024)
- [SelfElicit: Your Language Model Secretly Knows Where is the Relevant Evidence](https://mlsanity.com/paper/2502.08767/) (2025)
- [Towards Context-Robust LLMs: A Gated Representation Fine-tuning Approach](https://mlsanity.com/paper/2502.14100/) (2025)
- [AmazonQAC: A Large-Scale, Naturalistic Query Autocomplete Dataset](https://mlsanity.com/paper/2411.04129/) (2024)

## Built on by (most cited first, 1 of 1)

- [Magnifying What Matters: Attention-Guided Adaptive Rendering for Visual Text Comprehension](https://mlsanity.com/paper/2606.12898/) (2026)

## Abstract (arXiv)

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.