Skip to main content

🏢 Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences

DeepRAG: Thinking to Retrieval Step by Step for Large Language Models
·2973 words·14 mins· loading · loading
AI Generated 🤗 Daily Papers Natural Language Processing Question Answering 🏢 Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences
DeepRAG enhances LLM reasoning by strategically integrating retrieval, modeled as an MDP, improving accuracy by 21.99% and retrieval efficiency.