MvP-ECR: Multi-Perspective Emotion-Cause Reasoning for Empathetic Dialogue
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (3) · 1819-1827
DOI: 10.1609/aaai.v40i3.37161 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yuanyuan He und 5 weiteren Autor:innen.
Abstract (Originalsprache)
The empathetic dialogue systems aim to recognize user emotions and generate appropriate empathetic responses. However, existing approaches predominantly rely on dialogue history, contextual descriptions, and emotion category labels, failing to model the causal relationship between emotions and their underlying triggers. This limitation leads to generated responses that lack grounding, exhibit weak relevance, and suffer from poor interpretability in emotional expression. To address this, we propose MvP-ECR, a multi-perspective emotion cause reasoning framework that explicitly constructs emotion-cause structures to help models focus on the core emotional drivers. Additionally, we introduce an emotion-cause consistency evaluation metric to quantitatively assess a model’s ability to identify causal relationships. Experiments across multiple large language models (LLMs) demonstrate that the MvP-ECR framework can serve as a plug-and-play tool to help the model correctly infer emotions and causes in empathetic conversations, and provide more immersive responses for empathetic responses. All code and data will be publicly released to promote the development of empathy dialogue research.
Zitieren
APA
He, Y., Huang, G., Li, W., You, J., Deng, J., & Ren, F. (2026). MvP-ECR: Multi-Perspective Emotion-Cause Reasoning for Empathetic Dialogue. Proceedings of the AAAI Conference on Artificial Intelligence, 40(3), 1819-1827. https://doi.org/10.1609/aaai.v40i3.37161
Vancouver
He Y, Huang G, Li W, You J, Deng J, Ren F. MvP-ECR: Multi-Perspective Emotion-Cause Reasoning for Empathetic Dialogue. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(3):1819-1827. doi:10.1609/aaai.v40i3.37161
BibTeX
@article{He2026,
author = {He, Yuanyuan and Huang, Guotai and Li, Wei and You, Jiali and Deng, Jiawen and Ren, Fuji},
title = {MvP-ECR: Multi-Perspective Emotion-Cause Reasoning for Empathetic Dialogue},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {3},
pages = {1819--1827},
doi = {10.1609/aaai.v40i3.37161}
}
EUVIMED