重新思考检索增强生成中的软压缩：从查询条件选择器视角
Rethinking Soft Compression in Retrieval-Augmented Generation: A Query-Conditioned Selector Perspective
AI总结：
本文提出SeleCom框架，通过查询条件选择器改进RAG中的软压缩，提升信息密度并减少计算开销，实验显示其性能优于现有方法且效率更高。
摘要：
检索增强生成（RAG）通过外部知识有效支撑大语言模型（LLMs），但其扩展性受限于过长的上下文和冗余检索。本文分析发现全压缩方案存在不可行性和非必要性，并提出基于选择器的软压缩框架SeleCom，通过查询条件选择器优化信息密度，实验表明其在性能和效率上均优于现有方法。
英文摘要：
Retrieval-Augmented Generation (RAG) effectively grounds Large Language Models (LLMs) with external knowledge and is widely applied to Web-related tasks. However, its scalability is hindered by excessive context length and redundant retrievals. Recent research on soft context compression aims to address this by encoding long documents into compact embeddings, yet they often underperform non-compressed RAG due to their reliance on auto-encoder-like full-compression that forces the encoder to compress all document information regardless of relevance to the input query. In this work, we conduct an analysis on this paradigm and reveal two fundamental limitations: (I) Infeasibility, full-compression conflicts with the LLM's downstream generation behavior; and (II) Non-necessity: full-compression is unnecessary and dilutes task-relevant information density. Motivated by these insights, we introduce SeleCom, a selector-based soft compression framework for RAG that redefines the encoder's role as query-conditioned information selector. The selector is decoder-only and is trained with a massive, diverse and difficulty-graded synthetic QA dataset with curriculum learning. Extensive experiments show that SeleCom significantly outperforms existing soft compression approaches and achieves competitive or superior performance to non-compression baselines, while reducing computation and latency by 33.8%~84.6%.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
