作者位次 #4/7ACL 2026Findings· Findings of ACL
Optimizing Conversational Quality in Spoken Dialogue Systems with Reinforcement Learning from AI Feedback
Siddhant Arora · Jinchuan Tian · Jiatong Shi · Hayato Futami · Yosuke Kashiwagi · Emiru Tsunoo · Shinji Watanabe
摘要
Reinforcement learning from human or AI feedback (RLHF/RLAIF) for speech-in/speech-out dialogue systems (SDS) remains underexplored, with prior work largely limited to single semantic rewards applied at the utterance level. Such setups overlook the multi-dimensional and multi-modal nature of conv...