Emotion recognition in conversation (ERC) is a task which predicts the emotion of an utterance in the context of a conversation. It tightly depends on dialogue context, speaker identity information, multiparty dialogue scenario and so on. However, the state-of-the-art method (instructERC) solely identifying speaker, and ignores commonsense knowledge(i.e., reaction of the listeners and intention of the speaker, etc.) behind speakers during a conversation, which can deeply mine speaker information. To this end, we propose a novel joint large language models with commonsense knowledge framework for emotion recognition in conversation, namely CKERC.We design prompts to generate interlocutors' commonsense based on historical utterances with large language model. And we use the interlocutor commonsense identification task for LLM pre-training to fine-tune speaker implicit clues information.By solving above challenge, our method achieve state-of-the-art.We extensive experiment on three widely-used datasets, i.e., IEMOCAP, MELD, EmoryNLP, demonstrate our method superiority. Also, we conduct in-depth analysis and further demonstrate the effectiveness of commonsense knowledge in ERC task in large language model.

翻译：对话情感识别（ERC）是一项在对话上下文中预测话语情感的任务。它紧密依赖于对话上下文、说话人身份信息、多方对话场景等因素。然而，现有最先进方法（instructERC）仅识别说话人身份，忽略了对话中说话人背后的常识知识（例如听众反应、说话人意图等），而后者能深度挖掘说话人信息。为此，我们提出一种新颖的联合大语言模型与常识知识框架用于对话情感识别，即CKERC。我们设计提示词，利用大语言模型基于历史话语生成对话参与者的常识。同时，采用对话参与者常识识别任务对大语言模型进行预训练，以微调说话人隐含线索信息。通过解决上述挑战，我们的方法达到了最先进性能。我们在三大广泛使用的数据集（IEMOCAP、MELD、EmoryNLP）上进行大量实验，证明了方法的优越性。此外，我们进行了深入分析，进一步验证了常识知识在大语言模型ERC任务中的有效性。