RL-Index: Reinforcement Learning for Retrieval Index Reasoning
RL-Index introduces an agentic indexing framework that shifts reasoning from query time to indexing stage by using LLM-generated rationales and reinforcement learning to improve re…
Hugging Face · Daily Papers
·Yongjia Lei, Nedim Lipka
·
·▲ 5 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Yongjia Lei, Nedim Lipka, Zhisheng Qi, Utkarsh Sahu, Koustava Goswami, Franck Dernoncourt
- 5 upvotes da comunidade
- Temas: reinforcement learning, Group Relative Policy Optimization, retrieval index reasoning, LLM-generated rationales, query-side reasoning, index-side reasoning
Resumo
Resumo original (em inglês), extraído do paper:
RL-Index introduces an agentic indexing framework that shifts reasoning from query time to indexing stage by using LLM-generated rationales and reinforcement learning to improve retrieval effectiveness and reduce latency.
