Comparative Analysis of Open-Source Language Models in Summarizing Medical Text Data
Open accessAbstract
Unstructured text in medical notes and dialogues contains rich information. Recent advancements in Large Language Models (LLMs) have demonstrated superior performance in question answering and summarization tasks on unstructured text data, outperforming traditional text analysis approaches. However, there is a lack of scientific studies in the literature that methodically evaluate and report on the performance of different LLMs, specifically for domain-specific data such as medical chart notes. We propose an evaluation approach to analyze the performance of open-source LLMs such as Llama2 and Mistral for medical summarization tasks, using GPT-4 as an assessor. Our innovative approach to quantitative evaluation of LLMs can enable quality control, support the selection of effective LLMs for specific tasks, and advance knowledge discovery in digital health.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Only a few studies report high consistency between LLM-as-a-judge and expert outputs that overall met the researchers' needs.
“However, only a few studies report high consistency between LLM-as-a-judge and expert outputs that overall met the researchers’ needs [22,23].”
From Evaluating Medical Text Summaries Using Automatic Evaluation Metrics and LLM-as-a-Judge Approach: A Pilot Study (2025) · cites this paper as [22]
Cites
(2004) · Cited by 9,718 · see citing works
Training language models to follow instructions with human feedback
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.02155 · Cited by 4,208 · see citing works
Llama 2: Open Foundation and Fine-Tuned Chat Models
Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2307.09288 · Cited by 2,604 · see citing works
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
Zheng, L., Chiang, W.-L., Sheng, Y., Zhuang, S., Wu, Z., Zhuang, Y., Lin, Z., Li, Z., Li, D., Xing, E. P., et al. (2023) · arXiv · doi:10.48550/arxiv.2306.05685 · Cited by 1,888 · see citing works
MedDialog: Large-scale Medical Dialogue Datasets
Zeng, G., Yang, W., Ju, Z., Yang, Y., Wang, S., Zhang, R., Zhou, M., Zeng, J., Dong, X., Zhang, R., et al. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.743 · Cited by 178 · see citing works
BioBART: Pretraining and Evaluation of A Biomedical Generative Language Model
Yuan, H., Yuan, Z., Gan, R., Zhang, J., Xie, Y., & Yu, S. (2022) · Workshop on Biomedical Language Processing (BioNLP) · doi:10.18653/v1/2022.bionlp-1.9 · Cited by 142 · see citing works
Large Language Models are not Fair Evaluators
Wang, P., Li, L., Chen, L., Cai, Z., Zhu, D., Lin, B., Cao, Y., Kong, L., Liu, Q., Liu, T., et al. (2024) · Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2024.acl-long.511 · Cited by 138 · see citing works
On the Summarization of Consumer Health Questions
Abacha, A. B., & Demner-Fushman, D. (2019) · Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1215 · Cited by 114 · see citing works
Question-driven summarization of answers to consumer health questions
Savery, M. E., Abacha, A. B., Gayen, S., & Demner‐Fushman, D. (2020) · Scientific Data · doi:10.1038/s41597-020-00667-z · Cited by 88 · see citing works
Overview of the MEDIQA 2021 Shared Task on Summarization in the Medical Domain
Abacha, A. B., Mrabet, Y., Zhang, Y., Shivade, C., Langlotz, C. P., & Demner‐Fushman, D. (2021) · Workshop on Biomedical Language Processing (BioNLP) · doi:10.18653/v1/2021.bionlp-1.8 · Cited by 67 · see citing works
Jahan, I., Laskar, M. T. R., Peng, C., & Huang, J. X. (2023) · Workshop on Biomedical Language Processing (BioNLP) · doi:10.18653/v1/2023.bionlp-1.30 · Cited by 45 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Vasilev, Y., Raznitsyna, I., Pamova, A., Burtsev, T., Bobrovskaya, T., Kosov, P., Vladzymyrskyy, A., Omelyanskaya, O., & Arzamasov, K. (2025) · Diagnostics · doi:10.3390/diagnostics16010003 · Cited by 5 · see citing works
“However, only a few studies report high consistency between LLM-as-a-judge and expert outputs that overall met the researchers’ needs [22,23].”
- Authors
- Chen, Y., Wang, Z., & Zulkernine, F.
- Affiliations
- Queen's University (CA)
- Venue
- 2024 IEEE International Conference on Digital Health (ICDH)
- Publisher
- IEEE
- Published
- 2024-07-07
- Pages
- 126-128
- OpenAlex
- W4401943459
- Cited by
- 15
- References
- 11
- Citations by year
- 2026: 1 · 2025: 10 · 2024: 4
- FWCI
- 4.33
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE International Conference on Digital Health (ICDH) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- open-source large language models, Llama 2, Mistral, LLM benchmarking, clinical text, digital health
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
