This paper presents a unified spoken language model for emotional intelligence, enhanced by a novel data construction strategy termed Injected Emotional-Attribution Thinking (IEAT). IEAT incorporates user emotional states and their underlying causes into the model's internal reasoning process, enabling emotion-aware reasoning to be internalized rather than treated as explicit supervision. The model is trained with a two-stage progressive strategy. The first stage performs speech-text alignment and emotional attribute modeling via self-distillation, while the second stage conducts end-to-end cross-modal joint optimization to ensure consistency between textual and spoken emotional expressions. Experiments on the Human-like Spoken Dialogue Systems Challenge (HumDial) Emotional Intelligence benchmark demonstrate that the proposed approach achieves top-ranked performance across emotional trajectory modeling, emotional reasoning, and empathetic response generation under both LLM-based and human evaluations.
@article{arxiv.2601.04960,
title = {A Unified Spoken Language Model with Injected Emotional-Attribution Thinking for Human-like Interaction},
author = {Qing Wang and Zehan Li and Yaodong Song and Hongjie Chen and Jian Kang and Jie Lian and Jie Li and Yongxiang Li and Xuelong Li},
journal= {arXiv preprint arXiv:2601.04960},
year = {2026}
}