The field of emotion recognition of conversation (ERC) has been focusing on separating sentence feature encoding and context modeling, lacking exploration in generative paradigms based on unified designs. In this study, we propose a novel approach, \textbf{InstructERC}, to reformulate the ERC task from a discriminative framework to a generative framework based on Large Language Models (LLMs). InstructERC makes three significant contributions: (1) it introduces a simple yet effective retrieval template module, which helps the model explicitly integrate multi-granularity dialogue supervision information. (2) We introduce two additional emotion alignment tasks, namely speaker identification and emotion prediction tasks, to implicitly model the dialogue role relationships and future emotional tendencies in conversations. (3) Pioneeringly, we unify emotion labels across benchmarks through the feeling wheel to fit real application scenarios. InstructERC still perform impressively on this unified dataset. Our LLM-based plugin framework significantly outperforms all previous models and achieves comprehensive SOTA on three commonly used ERC datasets. Extensive analysis of parameter-efficient and data-scaling experiments provides empirical guidance for applying it in practical scenarios. Our code and aligned unified dataset (UIME) can be found in the Github link.\footnote{You can find the offical realization in the Github link: https://github.com/LIN-SHANG/InstructERC}

翻译：对话情感识别领域长期聚焦于分离句子特征编码与上下文建模，缺乏基于统一设计的生成范式探索。本研究提出创新方法\textbf{InstructERC}，将情感识别任务从判别式框架重构为基于大语言模型（LLMs）的生成式框架。InstructERC做出三项重要贡献：（1）引入简洁高效的检索模板模块，帮助模型显式整合多粒度对话监督信息；（2）新增两个情感对齐任务——说话人识别与情感预测任务，隐式建模对话中的角色关系与未来情感倾向；（3）通过情绪轮盘首次跨基准统一情感标签，使其适配真实应用场景。在此统一数据集上，InstructERC仍表现优异。我们的LLM插件框架显著超越所有前人模型，在三个常用情感识别数据集上实现全面最优结果。参数高效与数据规模扩展实验的深入分析为实际场景应用提供了经验性指导。相关代码与对齐后的统一数据集（UIME）可在Github链接中获取。\footnote{官方实现见Github链接：https://github.com/LIN-SHANG/InstructERC}