Improving accuracy of GPT-3/4 results on biomedical data using a retrieval-augmented language model
Open accessThe DOI matches its Crossref record; 28 of the 28 references it cites were found in a registry or an index.
Abstract
Large language models (LLMs) have made a significant impact on the fields of general artificial intelligence. General purpose LLMs exhibit strong logic and reasoning skills and general world knowledge but can sometimes generate misleading results when prompted on specific subject areas. LLMs trained with domain-specific knowledge can reduce the generation of misleading information (i.e. hallucinations) and enhance the precision of LLMs in specialized contexts. Training new LLMs on specific corpora however can be resource intensive. Here we explored the use of a retrieval-augmented generation (RAG) model which we tested on literature specific to a biomedical research area. OpenAI’s GPT-3.5, GPT-4, Microsoft’s Prometheus, and a custom RAG model were used to answer 19 questions pertaining to diffuse large B-cell lymphoma (DLBCL) disease biology and treatment. Eight independent reviewers assessed LLM responses based on accuracy, relevance, and readability, rating responses on a 3-point scale for each category. These scores were then used to compare LLM performance. The performance of the LLMs varied across scoring categories. On accuracy and relevance, the RAG model outperformed other models with higher scores on average and the most top scores across questions. GPT-4 was more comparable to the RAG model on relevance versus accuracy. By the same measures, GPT-4 and GPT-3.5 had the highest scores for readability of answers when compared to the other LLMs. GPT-4 and 3.5 also had more answers with hallucinations than the other LLMs, due to non-existent references and inaccurate responses to clinical questions. Our findings suggest that an oncology research-focused RAG model may outperform general-purpose LLMs in accuracy and relevance when answering subject-related questions. This framework can be tailored to Q&A in other subject areas. Further research will help understand the impact of LLM architectures, RAG methodologies, and prompting techniques in answering questions across different subject areas.
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. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372 · cited 1×
“The development of large language models (LLMs), such as bidirectional encoder representations from transformer (BERT) and generative pre-trained transformer (GPT), has revolutionized the field of natural language processing [1], [2], [3] [4].”
BackgroundLoRA: Low-Rank Adaptation of Large Language Models
Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., & Chen, W. (2021) · arXiv · doi:10.48550/arxiv.2106.09685 · Cited by 13,453
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
Reimers, N., & Gurevych, I. (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/d19-1410 · Cited by 12,778 · cited 1×
“Word and sentence embeddings are high-dimensional numerical representations of concepts scaled by the size of the corpus and complexity of language usage [19] [20, 21].”
BackgroundExploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929
Scaling Laws for Neural Language Models
Kaplan, J., McCandlish, S., Henighan, T., Brown, T. B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., & Amodei, D. (2020) · arXiv · doi:10.48550/arxiv.2001.08361 · Cited by 9,550 · cited 1×
“The LLM architecture might also need to be updated to incorporate more parameters to memorize more facts [29].”
BackgroundBioBERT: a pre-trained biomedical language representation model for biomedical text mining
Lee, J., Yoon, W., Kim, S., Kim, D., Kim, S., So, C. H., & Kang, J. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btz682 · Cited by 7,218
On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜
Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445922 · Cited by 6,988 · cited 1×
“A corpus that predominantly features one type of language or cultural context may display bias towards that specific domain or culture [23].”
BackgroundLLaMA: 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
Chain-Of-Thought Prompting Elicits Reasoning in Large Language Models
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q. V., & Zhou, D. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-1800 · Cited by 4,505
Cited by
Retrieval augmented generation for large language models in healthcare: A systematic review
Amugongo, L. M., Mascheroni, P., Brooks, S., Doering, S., & Seidel, J. (2025) · PLOS Digital Health · doi:10.1371/journal.pdig.0000877 · Cited by 267
Wang, D., Liang, J., Ye, J., Li, J., Li, J., Zhang, Q., Hu, Q., Pan, C., Wang, D., Liu, Z., et al. (2024) · Journal of Medical Internet Research · doi:10.2196/58041 · Cited by 76
Xu, P., Chen, X., Zhao, Z., & Shi, D. (2024) · British Journal of Ophthalmology · doi:10.1136/bjo-2023-325054 · Cited by 63
GastroBot: a Chinese gastrointestinal disease chatbot based on the retrieval-augmented generation
Zhou, Q., Liu, C., Duan, Y., Sun, K., Li, Y., Kan, H., Gu, Z., Shu, J., & Hu, J. (2024) · Frontiers in Medicine · doi:10.3389/fmed.2024.1392555 · Cited by 44
“In recent years, RAG technology has proven effective in the biomedical field (16).”
BackgroundRetrieval-Augmented Generation: Advancing personalized care and research in oncology
Zarfati, M., Soffer, S., Nadkarni, G. N., & Klang, E. (2025) · European Journal of Cancer · doi:10.1016/j.ejca.2025.115341 · Cited by 20
Metadata
- Authors
- Soong, D., Sridhar, S., Si, H., Wagner, J.-S., Sá, A. C. C., Yu, C. Y., Karagoz, K., Guan, M., Kumar, S., Hamadeh, H., & Higgs, B. W.
- Venue
- PLOS Digital Health
- Publisher
- Public Library of Science (PLoS)
- Published
- 2024-08-21
- Volume
- 3
- Issue
- 8
- Pages
- e0000568
- ISSN
- 2767-3170 (ISSN-L)
- OpenAlex
- W4401726216
- Cited by
- 49
- References
- 28
- FWCI
- 3.85
- 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: Improving accuracy of GPT-3/4 results on biomedical data using a retrieval-augmented language model. https://app.cochat.ai/papers/10.1371/journal.pdig.0000568
- The paper
- Soong, D., Sridhar, S., Si, H., Wagner, J.-S., Sá, A. C. C., Yu, C. Y., Karagoz, K., Guan, M., Kumar, S., Hamadeh, H., & Higgs, B. W. (2024). Improving accuracy of GPT-3/4 results on biomedical data using a retrieval-augmented language model. PLOS Digital Health. https://doi.org/10.1371/journal.pdig.0000568
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.