Hallucination-Aware Multimodal Benchmark for Gastrointestinal Image Analysis with Large Vision-Language Models

Khanal, BidurPokhrel, SandeshBhandari, SanjayRana, RameshShrestha, NikeshGurung, Ram BahadurLinte, Cristian A.Watson, Angus J MShrestha, Yash RajBhattarai, Binod2025-07-012025-07-012025-06-22Khanal, B, Pokhrel, S, Bhandari, S, Rana, R, Shrestha, N, Gurung, R B, Linte, C A, Watson, A J M, Shrestha, Y R & Bhattarai, B 2025, 'Hallucination-Aware Multimodal Benchmark for Gastrointestinal Image Analysis with Large Vision-Language Models', Paper presented at 28th International Conference On Medical Image Computing And Computer Assisted Intervention, Daejon, Korea, Republic of, 23/09/25 - 27/09/25. https://doi.org/10.48550/arXiv.2505.07001conferencehttps://hdl.handle.net/2164/25656Submission history [v1] Sun, 11 May 2025 14:54:11 UTC (5,502 KB) [v2] Sun, 22 Jun 2025 20:58:41 UTC (5,502 KB) All accepted papers will be made available by Springer's Lecture Notes in Computer Science no earlier than two weeks prior to the conference.137441846engSubstantive connection via an eligible employment contractmultimodal dataGastrointestinal image analysisVision Language ModelHallucinationHallucination-aware finetuningQA75 Electronic computers. Computer scienceQA75Hallucination-Aware Multimodal Benchmark for Gastrointestinal Image Analysis with Large Vision-Language ModelsConference paper10.48550/arXiv.2505.07001https://conferences.miccai.org/2025/en/