Jury Duty: Calibration and Orientation Failures in MLLM-as-a-Judge Under Cultural Ambiguity
Daniel Lee, Harshit Sharma, Eunkyu Park, Pranav Narayanan, Jeonghwan Kim, Kah Mun, Andreas Vlachos, and Shafiq Joty. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP-26) 2026.
PDF BibTex Slides