SubmissionNumber#=%=#235 FinalPaperTitle#=%=#JMI at SemEval 2024 Task 3: Two-step approach for multimodal ECAC using in-context learning with GPT and instruction-tuned Llama models ShortPaperTitle#=%=# NumberOfPages#=%=#16 CopyrightSigned#=%=#Arefa JobTitle#==# Organization#==#Jamia Millia Islamia University Abstract#==#This paper presents our system development for SemEval-2024 Task 3: "The Competition of Multimodal Emotion Cause Analysis in Conversations". Effectively capturing emotions in human conversations requires integrating multiple modalities such as text, audio, and video. However, the complexities of these diverse modalities pose challenges for developing an efficient multimodal emotion cause analysis (ECA) system. Our proposed approach addresses these challenges by a two-step framework. We adopt two different approaches in our implementation. In Approach 1, we employ instruction-tuning with two separate Llama 2 models for emotion and cause prediction. In Approach 2, we use GPT-4V for conversation-level video description and employ in-context learning with annotated conversation using GPT 3.5. Our system wins rank 4, and system ablation experiments demonstrate that our proposed solutions achieve significant performance gains. Author{1}{Firstname}#=%=#Arefa Author{1}{Username}#=%=#arefa Author{1}{Email}#=%=#arefa2001@gmail.com Author{1}{Affiliation}#=%=#Jamia Millia Islamia University Author{2}{Firstname}#=%=#Mohammed Abbas Author{2}{Lastname}#=%=#Ansari Author{2}{Username}#=%=#m-abbas-ansari Author{2}{Email}#=%=#mohd.abbas.ansari.2001@gmail.com Author{2}{Affiliation}#=%=#Jamia Millia Islamia University Author{3}{Firstname}#=%=#Chandni Author{3}{Lastname}#=%=#Saxena Author{3}{Username}#=%=#cmooncs Author{3}{Email}#=%=#csaxena@cse.cuhk.edu.hk Author{3}{Affiliation}#=%=#The Chinese University of Hong Kong Author{4}{Firstname}#=%=#TANVIR Author{4}{Lastname}#=%=#AHMAD Author{4}{Username}#=%=#tanvir.ahmad Author{4}{Email}#=%=#tahmad2@jmi.ac.in Author{4}{Affiliation}#=%=#JAMIA MILLIA ISLAMIA, NEW DELHI, INDIA ========== èéáğö