Enhancing Emotional Generation Capability of Large Language Models via Emotional Chain-of-Thought

TL;DR

This paper introduces Emotional Chain-of-Thought (ECoT), a prompting method that improves large language models' emotional generation by aligning with human emotional intelligence, and proposes an automated evaluation metric called EGS.

Contribution

The paper presents ECoT as a novel plug-and-play prompting technique and EGS as an automated evaluation method, advancing emotional generation in LLMs.

Findings

ECoT significantly improves emotional generation performance.

EGS provides reliable, model-based evaluation aligned with emotional intelligence.

Experimental results confirm the effectiveness of ECoT and EGS.

Abstract

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.