Modeling and Benchmarking Spoken Dialogue Rewards with Modality and Colloquialness

ArXi:2603.14889v1 Announce Type: cross The rapid evolution of end-to-end spoken dialogue systems demands transcending mere textual semantics to incorporate paralinguistic nuances and the spontaneous nature of human conversation. However, current methods struggle with two critical gaps: the modality gap, involving prosody and emotion, and the colloquialness gap, distinguishing written scripts from natural speech. To address these challenges, we