CoChat

Small language models learn enhanced reasoning skills from medical textbooks

Open access
Kim, Hyunjae, Hwang, Hyeon, Lee, Jiwoo, Park, Sihyeon, Kim, Dain, Lee, Taewhoo, Yoon, Chanwoong, Sohn, Jiwoong, Park, Jungwoo, Reykhart, Olga, Fetherston, Thomas, Choi, Donghee, Kwak, Soo Heon, Chen, Qingyu, Kang, Jaewoo · 2025 · npj Digital Medicine
Cited by 59

The DOI matches its Crossref record; 39 of the 39 references it cites were found in a registry or an index.

Abstract

Small language models (SLM) offer promise for medical applications by addressing the privacy and hardware constraints of large language models; however, their limited parameters (often fewer than ten billion) hinder multi-step reasoning for complex medical tasks. This study presents Meerkat, a new family of medical SLMs designed to be lightweight while enhancing reasoning capabilities. We begin by designing an effective and efficient training method. This involves extracting high-quality chain-of-thought reasoning paths from 18 medical textbooks, which are then combined with diverse instruction-following datasets within the medical domain, totaling 441K training examples. Fine-tuning was conducted on open-source SLMs using this curated dataset. Our Meerkat-7B and Meerkat-8B models outperformed their counterparts by 22.3% and 10.6% across six exam datasets, respectively. They also improved scores on the NEJM Case Challenge from 7 to 16 and from 13 to 20, surpassing the human score of 13.7. Additionally, they demonstrated superiority in expert evaluations, excelling in all metrics-completeness, factuality, clarity, and logical consistency-of reasoning abilities.

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 · 10.1038/s41746-025-01653-8

Cites

39 of 39 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 39 references

Cited by

See all 59

Metadata

Authors
Kim, H., Hwang, H., Lee, J., Park, S., Kim, D., Lee, T., Yoon, C., Sohn, J., Park, J., Reykhart, O., Fetherston, T., Choi, D., Kwak, S. H., Chen, Q., & Kang, J.
Venue
npj Digital Medicine
Published
2025-05-02
Volume
8
Issue
1
Pages
240-240
ISSN
2398-6352 (ISSN-L)
OpenAlex
W4410028173
Cited by
59
References
39
FWCI
11.47
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: Small language models learn enhanced reasoning skills from medical textbooks. https://app.cochat.ai/papers/10.1038/s41746-025-01653-8
The paper
Kim, H., Hwang, H., Lee, J., Park, S., Kim, D., Lee, T., Yoon, C., Sohn, J., Park, J., Reykhart, O., Fetherston, T., Choi, D., Kwak, S. H., Chen, Q., & Kang, J. (2025). Small language models learn enhanced reasoning skills from medical textbooks. npj Digital Medicine. https://doi.org/10.1038/s41746-025-01653-8

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.