Gemini Goes to Med School: Exploring the Capabilities of Multimodal Large Language Models on Medical Challenge Problems & Hallucinations
Open accessThe DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
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 github.com/promptslab/RosettaEval
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Jin, D., Pan, E., Oufattole, N., Weng, W.-H., Fang, H., & Szolovits, P. (2021) · doi:10.20944/preprints202105.0498.v1 · Cited by 718
PubMedQA: A Dataset for Biomedical Research Question Answering
Jin, Q., Dhingra, B., Liu, Z., Cohen, W., & Lu, X. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1259 · Cited by 685
Med-HALT: Medical Domain Hallucination Test for Large Language Models
Pal, A., Umapathi, L. K., & Sankarasubbu, M. (2023) · arXiv · doi:10.48550/arxiv.2307.15343 · Cited by 152
Self-citation
Cited by
ChatGPT: The End of Online Exam Integrity?
Susnjak, T., & McIntosh, T. (2024) · Education Sciences · doi:10.3390/educsci14060656 · Cited by 189
Large language model for medical images: a survey of taxonomy, systematic review, and future trends
Wang, P., Lu, W., Lu, C., Zhou, R., Li, M., & Qin, L. (2025) · Big Data Mining and Analytics · doi:10.26599/bdma.2024.9020090 · Cited by 21
Marey, A., Saad, A. M., Tanas, Y., Ghorab, H., Niemierko, J., Backer, H., & Umair, M. (2025) · Egyptian Journal of Radiology and Nuclear Medicine · doi:10.1186/s43055-025-01452-x · Cited by 16
Metadata
- Authors
- Pal, A., & Sankarasubbu, M.
- Venue
- Proceedings of the 6th Clinical Natural Language Processing Workshop
- Published
- 2024
- Pages
- 21-46
- OpenAlex
- W4401042829
- Cited by
- 37
- References
- 3
- FWCI
- 10.39
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Gemini Goes to Med School: Exploring the Capabilities of Multimodal Large Language Models on Medical Challenge Problems & Hallucinations. https://app.cochat.ai/papers/10.18653/v1/2024.clinicalnlp-1.3
- The paper
- Pal, A., & Sankarasubbu, M. (2024). Gemini Goes to Med School: Exploring the Capabilities of Multimodal Large Language Models on Medical Challenge Problems & Hallucinations. Proceedings of the 6th Clinical Natural Language Processing Workshop. https://doi.org/10.18653/v1/2024.clinicalnlp-1.3
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.