Model Calibration for Emotion Detection

Mihaela Petre-Vlad, Cornelia Caragea, Florentina Hristea


Abstract
In this paper, we propose a unified approach to model calibration for emotion detection that exploits the complementary strengths of knowledge distillation and the MixUp data augmentation technique to enhance the trustworthiness of emotion detection models. Specifically, we use a MixUp method informed by training dynamics that generates augmented data by interpolating easy-to-learn with ambiguous samples based on their similarity and dissimilarity provided by saliency maps. We use this MixUp method to calibrate the teacher model in the first generation of the knowledge distillation process. To further calibrate the teacher models in each generation, we employ dynamic temperature scaling to update the temperature used for scaling the teacher predictions. We find that calibrating the teachers with our method also improves the calibration of the student models. We test our proposed method both in-distribution (ID) and out-of-distribution (OOD). To obtain better OOD performance, we further fine-tune our models with a simple MixUp method that interpolates a small number of OOD samples with ambiguous ID samples.
Anthology ID:
2025.findings-emnlp.1114
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
20442–20457
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.1114/
DOI:
Bibkey:
Cite (ACL):
Mihaela Petre-Vlad, Cornelia Caragea, and Florentina Hristea. 2025. Model Calibration for Emotion Detection. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 20442–20457, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Model Calibration for Emotion Detection (Petre-Vlad et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.1114.pdf
Checklist:
 2025.findings-emnlp.1114.checklist.pdf