Speech emotion recognition plays an important role in various applications. However, most existing approaches predict a single emotion label, oversimplifying the inherently ambiguous nature of human emotional expression. Recent large audio-language models show promise in generating richer outputs, but their reasoning ability for ambiguous emotional understanding remains limited. In this work, we reformulate ambiguous emotion recognition as a distributional reasoning problem and present the first systematic study of ambiguity-aware reasoning in LALMs. Our framework comprises two complementary components: an ambiguity-aware objective that aligns predictions with human perceptual distributions, and a structured ambiguity-aware chain-of-thought supervision that guides reasoning over emotional cues. Experiments on IEMOCAP and CREMA-D demonstrate consistent improvements across SFT, DPO, and GRPO training strategies.
@article{arxiv.2603.08230,
title = {Disentangling Reasoning in Large Audio-Language Models for Ambiguous Emotion Prediction},
author = {Xiaofeng Yu and Jiaheng Dong and Jean Honorio and Abhirup Ghosh and Hong Jia and Ting Dang},
journal= {arXiv preprint arXiv:2603.08230},
year = {2026}
}