作者位次 #4/8ACL 2026Findings· Findings of ACL
Beyond Overlap Metrics: Rewarding Reasoning and Preferences for Faithful Multi-Role Dialogue Summarization
Xiaoyong Mei · Tingting Zuo · Da Chen · Guangyu Hu · Xiangyu Wen · Chao Duan · Mingyan Zhang · Fudan Zheng
摘要
Multi-role dialogue summarization requires modeling complex interactions among multiple speakers while preserving role-specific information and factual consistency. However, most existing methods optimize for automatic metrics such as ROUGE and BERTScore, which favor surface-level imitation of re...