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

arXiv:2402.10073v1 Announce Type: new
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 …

abstract ai assistants arxiv assistants cognition conversational cs.cl current emotion emotional intelligence experience focus general general ai intelligence language language model language models large language large language model large language models llm matter perception roles type