Large Language Model Synergy for Ensemble Learning in Medical Question Answering: Design and Evaluation Study
Open accessThe DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index.
Abstract
Background: Large language models (LLMs) have demonstrated remarkable capabilities in natural language processing tasks, including medical question-answering (QA). However, individual LLMs often exhibit varying performance across different medical QA datasets. We benchmarked individual zero-shot LLMs (GPT-4, Llama2-13B, Vicuna-13B, MedLlama-13B, and MedAlpaca-13B) to assess their baseline performance. Within the benchmark, GPT-4 achieves the best 71% on MedMCQA (medical multiple-choice question answering dataset), Vicuna-13B achieves 89.5% on PubMedQA (a dataset for biomedical question answering), and MedAlpaca-13B achieves the best 70% among all, showing the potential for better performance across different tasks and highlighting the need for strategies that can harness their collective strengths. Ensemble learning methods, combining multiple models to improve overall accuracy and reliability, offer a promising approach to address this challenge. Objective: To develop and evaluate efficient ensemble learning approaches, we focus on improving performance across 3 medical QA datasets through our proposed two ensemble strategies. Methods: Our study uses 3 medical QA datasets: PubMedQA (1000 manually labeled and 11,269 test, with yes, no, or maybe answered for each question), MedQA-USMLE (Medical Question Answering dataset based on the United States Medical Licensing Examination; 12,724 English board-style questions; 1272 test, 5 options), and MedMCQA (182,822 training/4183 test questions, 4-option multiple choice). We introduced the LLM-Synergy framework, consisting of two ensemble methods: (1) a Boosting-based Weighted Majority Vote ensemble, refining decision-making by adaptively weighting each LLM and (2) a Cluster-based Dynamic Model Selection ensemble, dynamically selecting optimal LLMs for each query based on question-context embeddings and clustering. Results: Both ensemble methods outperformed individual LLMs across all 3 datasets. Specifically comparing the best individual LLM, the Boosting-based Majority Weighted Vote achieved accuracies of 35.84% on MedMCQA (+3.81%), 96.21% on PubMedQA (+0.64%), and 37.26% (tie) on MedQA-USMLE. The Cluster-based Dynamic Model Selection yields even higher accuracies of 38.01% (+5.98%) for MedMCQA, 96.36% (+1.09%) for PubMedQA, and 38.13% (+0.87%) for MedQA-USMLE. Conclusions: The LLM-Synergy framework, using 2 ensemble methods, represents a significant advancement in leveraging LLMs for medical QA tasks. Through effectively combining the strengths of diverse LLMs, this framework provides a flexible and efficient strategy adaptable to current and future challenges in biomedical informatics.
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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
LLaMA: Open and Efficient Foundation Language Models
Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.13971 · Cited by 4,602
A Survey on Evaluation of Large Language Models
Chang, Y., Wang, X., Wang, J., Wu, Y., Yang, L., Zhu, K., Chen, H., Yi, X., Wang, C., Wang, Y., et al. (2024) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3641289 · Cited by 4,254 · cited 1×
“They represent a significant milestone while dealing with NLP tasks [13], such as text generation [14,15], QA [4,7,14,16-20], Named Entity Recognition [21-25], and so on.”
Large Language Models Encode Clinical Knowledge
Singhal, K., Azizi, S., Tu, T., Mahdavi, S. S., Wei, J., Chung, H. W., Scales, N., Tanwani, A., Cole-Lewis, H., Pfohl, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2212.13138 · Cited by 4,083
Large language models encode clinical knowledge
Singhal, K., Azizi, S., Tu, T., Mahdavi, S. S., Wei, J., Chung, H. W., Scales, N., Tanwani, A., Cole-Lewis, H., Pfohl, S., et al. (2023) · Nature · doi:10.1038/s41586-023-06291-2 · Cited by 4,083
PaLM: Scaling Language Modeling with Pathways
Chowdhery, A., Narang, S., Devlin, J., Bosma, M., Mishra, G., Roberts, A., Barham, P., Chung, H. W., Sutton, C., Gehrmann, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2204.02311 · Cited by 2,590
Domain-specific language model pretraining for biomedical natural language processing
Gu, Y., Tinn, R., Cheng, H., Lucas, M., Usuyama, N., Liu, X., Naumann, T., Gao, J., & Poon, H. (2022) · ACM Transactions on Computing for Healthcare · doi:10.1145/3458754 · Cited by 2,170 · cited 1×
“This integration must consider factors such as the compatibility of different models, the method of aggregating their outputs, and maintaining the interpretability of the responses [42-46].”
Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks
Gururangan, S., Marasović, A., Swayamdipta, S., Lo, K., Beltagy, I., Downey, D., & Smith, N. A. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.740 · Cited by 2,103
Alsentzer, E., Murphy, J., Boag, W., Weng, W.-H., Jindi, D., Naumann, T., & McDermott, M. (2019) · Proceedings of the 2nd Clinical Natural Language Processing Workshop · doi:10.18653/v1/w19-1909 · Cited by 1,736 · cited 1×
“We then tokenize each question context using a common tokenizer model (in our case, Clinical-BERT [59], which was pretrained on large-scale clinical notes and outperformed general biomedical models, was chosen since it matches our Medical QA situation very well), transforming the textual…”
Sparks of Artificial General Intelligence: Early experiments with GPT-4
Bubeck, S., Chandrasekaran, V., Eldan, R., Gehrke, J., Horvitz, E., Kamar, E., Lee, P., Lee, Y. T., Li, Y., Lundberg, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.12712 · Cited by 1,526
Cited by
Omar, M., Agbareia, R., Glicksberg, B. S., Nadkarni, G. N., & Klang, E. (2025) · JMIR Medical Informatics · doi:10.2196/66917 · Cited by 53
Automating expert-level medical reasoning evaluation of large language models
Zhou, S., Xie, W., Li, J., Zhan, Z., Song, M., Yang, H., Espinoza, C., Welton, L., Mai, X., Jin, Y., et al. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-02208-7 · Cited by 30
Self-citationCombining Multiple Large Language Models Improves Diagnostic Accuracy
Barabucci, G., Shia, V., Chu, E., Harack, B., Laskowski, K., & Fu, N. (2024) · NEJM AI · doi:10.1056/aics2400502 · Cited by 24
Benchmarking the Confidence of Large Language Models in Clinical Questions
Omar, M., Agbareia, R., Glicksberg, B. S., Nadkarni, G. N., & Klang, E. (2024) · doi:10.1101/2024.08.11.24311810 · Cited by 10
Correlated Errors in Large Language Models
Kim, E., Garg, A., Peng, K., & Garg, N. (2025) · arXiv · doi:10.48550/arxiv.2506.07962 · Cited by 4
Metadata
- Authors
- Yang, H., Li, M., Zhou, H., Xiao, Y., Fang, Q., Zhou, S., & Zhang, R.
- Venue
- Journal of Medical Internet Research
- Publisher
- JMIR Publications Inc.
- Published
- 2025-07-14
- Volume
- 27
- Pages
- e70080-e70080
- ISSN
- 1438-8871 (ISSN-L)
- OpenAlex
- W4410311153
- Cited by
- 60
- References
- 35
- FWCI
- 22.05
- Type
- journal article
- Language
- en
- Open access
- gold
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: Large Language Model Synergy for Ensemble Learning in Medical Question Answering: Design and Evaluation Study. https://app.cochat.ai/papers/10.2196/70080
- The paper
- Yang, H., Li, M., Zhou, H., Xiao, Y., Fang, Q., Zhou, S., & Zhang, R. (2025). Large Language Model Synergy for Ensemble Learning in Medical Question Answering: Design and Evaluation Study. Journal of Medical Internet Research. https://doi.org/10.2196/70080
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.