@inproceedings{molfese-etal-2025-right, title = "Right Answer, Wrong Score: Uncovering the Inconsistencies of {LLM} Evaluation in Multiple-Choice Question Answering", author = "Molfese, Francesco Maria and Moroni, Luca and Gioffr{\'e}, Luca and Scir{\`e}, Alessandro and Conia, Simone and Navigli, Roberto", editor = "Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher", booktitle = "Findings of the Association for Computational Linguistics: ACL 2025", month = jul, year = "2025", address = "Vienna, Austria", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/display_plenaries/2025.findings-acl.950/", pages = "18477--18494", ISBN = "979-8-89176-256-5" }