CoChat

Improving accuracy of GPT-3/4 results on biomedical data using a retrieval-augmented language model

Open access
Soong, David, Sridhar, Sriram, Si, Han, Wagner, Jan-Samuel, Sá, Ana Caroline Costa, Yu, Christina Y., Karagoz, Kubra, Guan, Meijian, Kumar, Sanyam, Hamadeh, Hisham, Higgs, Brandon W. · 2024 · PLOS Digital Health
Cited by 49

The 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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1371/journal.pdig.0000568

Cites

28 of 28 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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

Show all 28 references

Cited by

See all 49

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
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.