Both Matter: Enhancing the Emotional Intelligence of Large Language Models without Compromising the General Intelligence

Weixiang Zhao, Zhuojun Li, Shilong Wang, Yang Wang, Yulin Hu, Yanyan Zhao, Chen Wei, Bing Qin


Abstract
Emotional Intelligence (EI), consisting of emotion perception, emotion cognition and emotion expression, plays the critical roles in improving user interaction experience for the current large language model (LLM) based conversational general AI assistants. Previous works mainly focus on raising the emotion perception ability of them via naive fine-tuning on EI-related classification or regression tasks. However, this leads to the incomplete enhancement of EI and catastrophic forgetting of the general intelligence (GI). To this end, we first introduce EiBench, a large-scale collection of EI-related tasks in the text-to-text format with task instructions that covers all three aspects of EI, which lays a solid foundation for the comprehensive EI enhancement of LLMs. Then a novel Modular Emotional Intelligence enhancement method (**MoEI**), consisting of Modular Parameter Expansion and intra-inter modulation, is proposed to comprehensively enhance the EI of LLMs without compromise their GI. Extensive experiments on two representative LLM-based assistants, Flan-T5 and LLaMA-2-Chat, demonstrate the effectiveness of MoEI to improving EI while maintain GI.
Anthology ID:
2024.findings-acl.665
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11157–11176
Language:
URL:
https://aclanthology.org/2024.findings-acl.665
DOI:
10.18653/v1/2024.findings-acl.665
Bibkey:
Cite (ACL):
Weixiang Zhao, Zhuojun Li, Shilong Wang, Yang Wang, Yulin Hu, Yanyan Zhao, Chen Wei, and Bing Qin. 2024. Both Matter: Enhancing the Emotional Intelligence of Large Language Models without Compromising the General Intelligence. In Findings of the Association for Computational Linguistics: ACL 2024, pages 11157–11176, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Both Matter: Enhancing the Emotional Intelligence of Large Language Models without Compromising the General Intelligence (Zhao et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-acl.665.pdf