How to Retrieve Examples in In-context Learning to Improve Conversational Emotion Recognition using Large Language Models?

TL;DR

This paper investigates how to improve conversational emotion recognition using large language models by retrieving high-quality examples in in-context learning, demonstrating that augmented retrieval strategies enhance accuracy across multiple datasets.

Contribution

The study introduces augmented example retrieval methods for in-context learning that significantly improve conversational emotion recognition performance in LLMs.

Findings

Augmented retrieval outperforms random and other retrieval methods.

Retrieving coherent, paraphrased examples enhances CER accuracy.

The approach is effective across multiple datasets.

Abstract

Large language models (LLMs) have enabled a wide variety of real-world applications in various domains. However, creating a high-performing application with high accuracy remains challenging, particularly for subjective tasks like emotion recognition. Inspired by the SLT 2024 GenSER Challenge, this study investigates approaches to improving conversational emotion recognition (CER) by LLMs. Specifically, we explore how to retrieve high-quality examples in in-context learning (ICL) to enhance CER. We propose various strategies based on random and augmented example retrieval and also analyze the impact of conversational context on CER accuracy. Experiments were conducted on the three datasets including IEMOCAP, MELD and EmoryNLP. The results show that augmented example retrieval consistently outperforms other techniques under investigation across all datasets, highlighting the importance of retrieving coherent targeted examples and enhancing them through paraphrasing.