Tag
CoGR is a retrieval framework that uses co-evolving reinforcement learning to train LLMs for generating keywords in both query and item sides, achieving significant performance improvements in retrieval tasks.
Garry Tan highlights a retrieval system that uniquely combines keyword matching, graph traversal, and gap analysis, an approach not seen elsewhere.
The article argues against overusing vector search, highlighting BM25's effectiveness for exact keyword matching and its role in hybrid search systems.