EmoS: A Theory-Grounded Framework for Evaluating and Aligning Emotional Intelligence in Spoken Language Models
EmoDialogue, a bilingual dataset providing necessary fine-grained supervision through response pairs with rigorously defined EI gradations, and EmoS, a specialized evaluator model optimized via Supervised Fine-Tuning and Group Relative Policy Optimization, are introduced, establishing a foundational framework for advancing emotionally intelligent dialogue systems.