SubmissionNumber#=%=#295 FinalPaperTitle#=%=#SemEval-2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials ShortPaperTitle#=%=# NumberOfPages#=%=#16 CopyrightSigned#=%=#mael jullien JobTitle#==# Organization#==#The University of Manchester Oxford Rd, Manchester M13 9PL Abstract#==#Large Language Models (LLMs) are at the forefront of NLP achievements but fall short in dealing with shortcut learning, factual inconsistency, and vulnerability to adversarial inputs. These shortcomings are especially critical in medical contexts, where they can misrepresent actual model capabilities. Addressing this, we present SemEval-2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials. Our contributions include the refined NLI4CT-P dataset (i.e. Natural Language Inference for Clinical Trials - Perturbed), designed to challenge LLMs with interventional and causal reasoning tasks, along with a comprehensive evaluation of methods and results for participant submissions. A total of 106 participants registered for the task contributing to over 1200 individual submissions and 25 system overview papers. This initiative aims to advance the robustness and applicability of NLI models in healthcare, ensuring safer and more dependable AI assistance in clinical decision-making. We anticipate that the dataset, models, and outcomes of this task can support future research in the field of biomedical NLI. The dataset, competition leaderboard, and website are publicly available. Author{1}{Firstname}#=%=#Mael Author{1}{Lastname}#=%=#Jullien Author{1}{Username}#=%=#mjullien Author{1}{Email}#=%=#mael.jullien@postgrad.manchester.ac.uk Author{1}{Affiliation}#=%=#university of Manchester Author{2}{Firstname}#=%=#Marco Author{2}{Lastname}#=%=#Valentino Author{2}{Username}#=%=#mvalentino91 Author{2}{Email}#=%=#marco.valentino@idiap.ch Author{2}{Affiliation}#=%=#Idiap Research Institute Author{3}{Firstname}#=%=#André Author{3}{Lastname}#=%=#Freitas Author{3}{Username}#=%=#andre.freitas_1 Author{3}{Email}#=%=#andre.freitas@manchester.ac.uk Author{3}{Affiliation}#=%=#University of Manchester ========== èéáğö