AI RESEARCH
Rethinking Soft Compression in Retrieval-Augmented Generation: A Query-Conditioned Selector Perspective
arXiv CS.AI
•
ArXi:2602.15856v2 Announce Type: replace-cross 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.