SubmissionNumber#=%=#83 FinalPaperTitle#=%=#Samsung Research China-Beijing at SemEval-2024 Task 3: A multi-stage framework for Emotion-Cause Pair Extraction in Conversations ShortPaperTitle#=%=# NumberOfPages#=%=#11 CopyrightSigned#=%=#Shen Zhang JobTitle#==# Organization#==#Name: Samsung R&D Institute China-Beijing Address: GrandVic Building(Guanjie Tower), No.16, Taiyanggong Middle Road, Chaoyang District, Beijing, 100022, China Abstract#==#In human-computer interaction, it is crucial for agents to respond to human by understanding their emotions. unraveling the causes of emotions is more challenging. A new task named Multimodal Emotion-Cause Pair Extraction in Conversations is responsible for recognizing emotion and identifying causal expressions. In this study, we propose a multi-stage framework to generate emotion and extract the emotion causal pairs given the target emotion. In the first stage, LLaMA2-based InstructERC is utilized to extract the emotion category of each utterance in a conversation. After emotion recognition, a two-stream attention model is employed to extract the emotion causal pairs given the target emotion for subtask 2 while MuTEC is employed to extract causal span for subtask 1. Our approach achieved first place for both of the two subtasks in the competition. Author{1}{Firstname}#=%=#Shen Author{1}{Lastname}#=%=#Zhang Author{1}{Username}#=%=#mercurialzs Author{1}{Email}#=%=#ne1234@126.com Author{1}{Affiliation}#=%=#Samsung Research China-Beijing Author{2}{Firstname}#=%=#Haojie Author{2}{Lastname}#=%=#Zhang Author{2}{Email}#=%=#tayee.chang@samsung.com Author{2}{Affiliation}#=%=#Samsung Research China-Beijing Author{3}{Firstname}#=%=#Jing Author{3}{Lastname}#=%=#Zhang Author{3}{Email}#=%=#jing97.zhang@samsung.com Author{3}{Affiliation}#=%=#Samsung Research China-Beijing Author{4}{Firstname}#=%=#Xudong Author{4}{Lastname}#=%=#Zhang Author{4}{Email}#=%=#xudong.z1@samsung.com Author{4}{Affiliation}#=%=#Samsung Research China-Beijing Author{5}{Firstname}#=%=#Yimeng Author{5}{Lastname}#=%=#Zhuang Author{5}{Email}#=%=#ym.zhuang@samsung.com Author{5}{Affiliation}#=%=#Samsung Research China-Beijing Author{6}{Firstname}#=%=#Jinting Author{6}{Lastname}#=%=#Wu Author{6}{Email}#=%=#jinting01.wu@samsung.com Author{6}{Affiliation}#=%=#Samsung Research China-Beijing ========== èéáğö