most citedDIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrieval

1 citations · 1 across the 3 of their papers we have counts for

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2026

CTRL-RAG: Contrastive Likelihood Reward Based Reinforcement Learning for Context-Faithful RAG Models

Zhehao Tan, Yihan Jiao, Dan Yang +8

With the growing use of Retrieval-Augmented Generation (RAG), training large language models (LLMs) for context-sensitive reasoning and faithfulness is increasingly important. Exis…