SubmissionNumber#=%=#21 FinalPaperTitle#=%=#HAMiSoN-Ensemble at ClimateActivism 2024: Ensemble of RoBERTa, Llama 2, and Multi-task for Stance Detection ShortPaperTitle#=%=# NumberOfPages#=%=# CopyrightSigned#=%=# JobTitle#==# Organization#==# Abstract#==#CASE @ EACL 2024 proposes a shared task on Stance and Hate Event Detection for Climate Activism discourse. For our participation in the stance detection task, we propose an ensemble of different approaches: a transformer-based model (RoBERTa), a generative Large Language Model (Llama 2), and a Multi-Task Learning model. Our main goal is twofold: to study the effect of augmenting the training data with external datasets, and to examine the contribution of several, diverse models through a voting ensemble. The results show that if we take the best configuration during training for each of the three models (RoBERTa, Llama 2 and MTL), the ensemble would have ranked first with the highest F1 on the leaderboard for the stance detection subtask. Author{1}{Firstname}#=%=#Raquel Author{1}{Lastname}#=%=#Rodriguez-Garcia Author{1}{Username}#=%=#raquelr Author{1}{Email}#=%=#rrodriguez@lsi.uned.es Author{1}{Affiliation}#=%=#NLP & IR Group, UNED Author{2}{Firstname}#=%=#Julio Author{2}{Lastname}#=%=#Reyes Montesinos Author{2}{Username}#=%=#julioremo Author{2}{Email}#=%=#jreyes@lsi.uned.es Author{2}{Affiliation}#=%=#NLP & IR Group, UNED Author{3}{Firstname}#=%=#Jesus M. Author{3}{Lastname}#=%=#Fraile-Hernandez Author{3}{Username}#=%=#jfraile Author{3}{Email}#=%=#jfraile@lsi.uned.es Author{3}{Affiliation}#=%=#NLP & IR Group, UNED Author{4}{Firstname}#=%=#Anselmo Author{4}{Lastname}#=%=#Peñas Author{4}{Username}#=%=#anselmo Author{4}{Email}#=%=#anselmo@lsi.uned.es Author{4}{Affiliation}#=%=#NLP & IR Group, UNED ========== èéáğö