@inproceedings{wang-etal-2024-answer-c, title = "{\textquotedblleft}My Answer is {C}{\textquotedblright}: First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models", author = {Wang, Xinpeng and Ma, Bolei and Hu, Chengzhi and Weber-Genzel, Leon and R{\"o}ttger, Paul and Kreuter, Frauke and Hovy, Dirk and Plank, Barbara}, editor = "Ku, Lun-Wei and Martins, Andre and Srikumar, Vivek", booktitle = "Findings of the Association for Computational Linguistics: ACL 2024", month = aug, year = "2024", address = "Bangkok, Thailand", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2024.findings-acl.441/", doi = "10.18653/v1/2024.findings-acl.441", pages = "7407--7416" }