Do LLMs Feel? Teaching Emotion Recognition with Prompts, Retrieval, and Curriculum Learning

TL;DR

This paper introduces PRC-Emo, a novel training framework for emotion recognition in conversation using prompt engineering, retrieval, and curriculum learning, achieving state-of-the-art results on benchmark datasets.

Contribution

It presents a new ERC training method combining emotion-sensitive prompts, a dedicated retrieval repository, and curriculum learning for improved LLM emotional understanding.

Findings

Achieves new state-of-the-art performance on IEMOCAP and MELD datasets.

Demonstrates effectiveness of combining prompts, retrieval, and curriculum learning.

Shows improved perception of explicit and implicit emotions in conversational AI.

Abstract

Emotion Recognition in Conversation (ERC) is a crucial task for understanding human emotions and enabling natural human-computer interaction. Although Large Language Models (LLMs) have recently shown great potential in this field, their ability to capture the intrinsic connections between explicit and implicit emotions remains limited. We propose a novel ERC training framework, PRC-Emo, which integrates Prompt engineering, demonstration Retrieval, and Curriculum learning, with the goal of exploring whether LLMs can effectively perceive emotions in conversational contexts. Specifically, we design emotion-sensitive prompt templates based on both explicit and implicit emotional cues to better guide the model in understanding the speaker's psychological states. We construct the first dedicated demonstration retrieval repository for ERC, which includes training samples from widely used datasets, as well as high-quality dialogue examples generated by LLMs and manually verified. Moreover, we introduce a curriculum learning strategy into the LoRA fine-tuning process, incorporating weighted emotional shifts between same-speaker and different-speaker utterances to assign difficulty levels to dialogue samples, which are then organized in an easy-to-hard training sequence. Experimental results on two benchmark datasets -- IEMOCAP and MELD -- show that our method achieves new state-of-the-art (SOTA) performance, demonstrating the effectiveness and generalizability of our approach in improving LLM-based emotional understanding.