作者位次 #2/7ACL 2026Poster· Natural Language Processing
Reinforced Informativeness Optimization for Long-Form Retrieval-Augmented Generation
Yuhao Wang · Ruiyang Ren · Yucheng Wang · Wayne Xin Zhao · Jing Liu · hua wu · Haifeng Wang
摘要
Long-form question answering (LFQA) requires open-ended long-form responses that synthesize coherent, factually grounded content from multi-source evidence. This makes reinforcement learning (RL) reward design critical. The reward must be verifiable for faithful grounding and stable optimization....