如何通过上下文学习中的示例检索来提升大型语言模型的对话情感识别能力？
How to Retrieve Examples in In-context Learning to Improve Conversational Emotion Recognition using Large Language Models?
AI总结：
本研究探讨如何通过上下文学习中的示例检索提升大型语言模型的对话情感识别能力，提出基于随机和增强的检索策略，实验证明增强示例检索在三个数据集上均表现最优。
摘要：
大型语言模型（LLMs）在各领域的实际应用中展现了广泛潜力。然而，构建高准确率的高性能应用仍具挑战，尤其是对于情感识别等主观任务。受 SLT 2024 GenSER Challenge 启发，本研究探讨了提升 LLMs 对话情感识别（CER）的方法。具体而言，我们探索了如何在上下文学习（ICL）中检索高质量示例以增强 CER。我们提出了基于随机和增强示例检索的多种策略，并分析了对话上下文对 CER 准确率的影响。实验在 IEMOCAP、MELD 和 EmoryNLP 三个数据集上进行。结果表明，增强示例检索在所有数据集上均优于其他研究技术，突显了检索连贯目标示例并通过改写增强的重要性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
