@inproceedings{balepur-etal-2026-check, title = "Check The Scoreboard: An Analysis of Scoring Schemes on Multiple-Choice Evaluation", author = "Balepur, Nishant and Xu, Paiheng and Ai, Wei and Choi, Eunsol and Rudinger, Rachel and Boyd-Graber, Jordan", editor = "Lee, Hung-Yi and Dev, Sunipa and Li, Jessy and Elliott, Desmond", booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing", month = oct, year = "2026", address = "Budapest, Hungary", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2026.emnlp-main.11/", pages = "246--276", ISBN = "979-8-89176-459-0" }