作者位次 #2/9ACL 2026Poster· ACL Industry Track
R ³ A : Reinforced Reasoning for Relevance Assessment for RAG in User-Generated Content Platforms
Xiaowei Yuan · Lei Jin · Haoxin Zhang · Ziyang Huang · Yan Gao · Yi Wu · Yao Hu · Jun Zhao · Kang Liu
摘要
Retrieval-augmented generation (RAG) plays a critical role in user-generated content (UGC) platforms, but its effectiveness critically depends on accurate query–document relevance assessment. Despite recent advances in applying large language models (LLMs) to relevance modeling, UGC platforms pre...