Enhancing Emotional Generation Capability of Large Language Models via Emotional Chain-of-Thought
This addresses emotional generation tasks for AI applications, but it is incremental as it builds on existing prompting techniques.
The paper tackles the problem of improving emotional generation in large language models by proposing Emotional Chain-of-Thought (ECoT), a prompting method that aligns with human emotional intelligence guidelines, and introduces an automated evaluation method called Emotional Generation Score (EGS) based on Goleman's theory, showing effectiveness in experiments.
Large Language Models (LLMs) have shown remarkable performance in various emotion recognition tasks, thereby piquing the research community's curiosity for exploring their potential in emotional intelligence. However, several issues in the field of emotional generation tasks remain unresolved, including human preference alignment and emotional generation assessment. In this paper, we propose the Emotional Chain-of-Thought (ECoT), a plug-and-play prompting method that enhances the performance of LLMs on various emotional generation tasks by aligning with human emotional intelligence guidelines. To assess the reliability of ECoT, we propose an automated model-based evaluation method called Emotional Generation Score (EGS). EGS incorporates Goleman's Emotional Intelligence Theory as a consensus of human experts, providing a new perspective on the evaluation of emotional generation tasks. Extensive experimental results demonstrate the effectiveness of ECoT and EGS. Further, we discuss the promise of LLMs in the field of emotional intelligence and present key insights into the LLMs with the ECoT in emotional generation tasks.