Gemini Goes to Med School: Exploring the Capabilities of Multimodal Large Language Models on Medical Challenge Problems & Hallucinations

Ankit Pal, Malaikannan Sankarasubbu


Abstract
Large language models have the potential to be valuable in the healthcare industry, but it’s crucial to verify their safety and effectiveness through rigorous evaluation. In our study, we evaluated LLMs, including Google’s Gemini, across various medical tasks. Despite Gemini’s capabilities, it underperformed compared to leading models like MedPaLM 2 and GPT-4, particularly in medical visual question answering (VQA), with a notable accuracy gap (Gemini at 61.45% vs. GPT-4V at 88%). Our analysis revealed that Gemini is highly susceptible to hallucinations, overconfidence, and knowledge gaps, which indicate risks if deployed uncritically. We also performed a detailed analysis by medical subject and test type, providing actionable feedback for developers and clinicians. To mitigate risks, we implemented effective prompting strategies, improving performance, and contributed to the field by releasing a Python module for medical LLM evaluation and establishing a leaderboard on Hugging Face for ongoing research and development. Python module can be found at https://github.com/promptslab/RosettaEval
Anthology ID:
2024.clinicalnlp-1.3
Volume:
Proceedings of the 6th Clinical Natural Language Processing Workshop
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Tristan Naumann, Asma Ben Abacha, Steven Bethard, Kirk Roberts, Danielle Bitterman
Venues:
ClinicalNLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
21–46
Language:
URL:
https://aclanthology.org/2024.clinicalnlp-1.3
DOI:
10.18653/v1/2024.clinicalnlp-1.3
Bibkey:
Cite (ACL):
Ankit Pal and Malaikannan Sankarasubbu. 2024. Gemini Goes to Med School: Exploring the Capabilities of Multimodal Large Language Models on Medical Challenge Problems & Hallucinations. In Proceedings of the 6th Clinical Natural Language Processing Workshop, pages 21–46, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Gemini Goes to Med School: Exploring the Capabilities of Multimodal Large Language Models on Medical Challenge Problems & Hallucinations (Pal & Sankarasubbu, ClinicalNLP-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.clinicalnlp-1.3.pdf