上下文示例至关重要：通过指令微调改进对话中的情感识别
In-Context Examples Matter: Improving Emotion Recognition in Conversation with Instruction Tuning
AI总结：
本文提出单阶段上下文指令微调框架InitERC，通过上下文示例学习说话人、上下文与情感的对齐，在三个数据集上显著超越现有基线。
摘要：
对话中的情感识别（ERC）旨在识别对话中每句话语的情感，在共情人工智能中发挥着重要作用。随着大语言模型（LLMs）的发展，指令微调已成为ERC的关键范式。现有研究主要关注多阶段指令微调，即首先赋予LLMs说话人特征，然后进行上下文感知的指令微调以理解情感状态。然而，这些方法本质上限制了在统一框架内联合捕捉说话人特征与对话上下文之间动态交互的能力，导致说话人身份、上下文线索和情感状态之间的对齐较弱。本文提出InitERC，一个简单而有效的单阶段上下文指令微调框架，用于ERC。InitERC通过上下文指令微调使LLMs从上下文示例中学习说话人-上下文-情感对齐。具体而言，InitERC包含四个组成部分：演示池构建、上下文示例选择、提示模板设计和上下文指令微调。为探究上下文示例的影响，我们对三个关键因素进行了全面研究：检索策略、示例排序和示例数量。在三个广泛使用的数据集上的大量实验表明，我们提出的InitERC相比最先进的基线方法取得了显著改进。
英文摘要：
Emotion recognition in conversation (ERC) aims to identify the emotion of each utterance in a conversation, playing a vital role in empathetic artificial intelligence. With the growing of large language models (LLMs), instruction tuning has emerged as a critical paradigm for ERC. Existing studies mainly focus on multi-stage instruction tuning, which first endows LLMs with speaker characteristics, and then conducts context-aware instruction tuning to comprehend emotional states. However, these methods inherently constrains the capacity to jointly capture the dynamic interaction between speaker characteristics and conversational context, resulting in weak alignment among speaker identity, contextual cues, and emotion states within a unified framework. In this paper, we propose InitERC, a simple yet effective one-stage in-context instruction tuning framework for ERC. InitERC adapts LLMs to learn speaker-context-emotion alignment from context examples via in-context instruction tuning. Specifically, InitERC comprises four components, i.e., demonstration pool construction, in-context example selection, prompt template design, and in-context instruction tuning. To explore the impact of in-context examples, we conduct a comprehensive study on three key factors: retrieval strategy, example ordering, and the number of examples. Extensive experiments on three widely used datasets demonstrate that our proposed InitERC achieves substantial improvements over the state-of-the-art baselines.
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。
