Small Language Models Can Use Nuanced Reasoning For Health Science Research Classification: A Microbial-Oncogenesis Case Study

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dawood, Muhammed Muaaz, Moonsamy, Mohammad Zaid, Kokkas, Kaela, Wang, Hairong, Breiman, Robert F., Klein, Richard, Sekyi, Emmanuel K., Bassett, Bruce A.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912753160028160
author Dawood, Muhammed Muaaz
Moonsamy, Mohammad Zaid
Kokkas, Kaela
Wang, Hairong
Breiman, Robert F.
Klein, Richard
Sekyi, Emmanuel K.
Bassett, Bruce A.
author_facet Dawood, Muhammed Muaaz
Moonsamy, Mohammad Zaid
Kokkas, Kaela
Wang, Hairong
Breiman, Robert F.
Klein, Richard
Sekyi, Emmanuel K.
Bassett, Bruce A.
contents Artificially intelligent (AI) co-scientists must be able to sift through research literature cost-efficiently while applying nuanced scientific reasoning. We evaluate Small Language Models (SLMs, <= 8B parameters) for classifying medical research papers. Using literature on the oncogenic potential of HMTV/MMTV-like viruses in breast cancer as a case study, we assess model performance with both zero-shot and in-context learning (ICL; few-shot prompting) strategies against frontier proprietary Large Language Models (LLMs). Llama 3 and Qwen2.5 outperform GPT-5 (API, low/high effort), Gemini 3 Pro Preview, and Meerkat in zero-shot settings, though trailing Gemini 2.5 Pro. ICL leads to improved performance on a case-by-case basis, allowing Llama 3 and Qwen2.5 to match Gemini 2.5 Pro in binary classification. Systematic lexical-ablation experiments show that SLM decisions are often grounded in valid scientific cues but can be influenced by spurious textual artifacts, underscoring need for interpretability in high-stakes pipelines. Our results reveal both promise and limitations of modern SLMs for scientific triage; pairing SLMs with simple but principled prompting strategies can approach performance of the strongest LLMs for targeted literature filtering in co-scientist pipelines.
format Preprint
id arxiv_https___arxiv_org_abs_2512_06502
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Small Language Models Can Use Nuanced Reasoning For Health Science Research Classification: A Microbial-Oncogenesis Case Study
Dawood, Muhammed Muaaz
Moonsamy, Mohammad Zaid
Kokkas, Kaela
Wang, Hairong
Breiman, Robert F.
Klein, Richard
Sekyi, Emmanuel K.
Bassett, Bruce A.
Computational Engineering, Finance, and Science
Quantitative Methods
Artificially intelligent (AI) co-scientists must be able to sift through research literature cost-efficiently while applying nuanced scientific reasoning. We evaluate Small Language Models (SLMs, <= 8B parameters) for classifying medical research papers. Using literature on the oncogenic potential of HMTV/MMTV-like viruses in breast cancer as a case study, we assess model performance with both zero-shot and in-context learning (ICL; few-shot prompting) strategies against frontier proprietary Large Language Models (LLMs). Llama 3 and Qwen2.5 outperform GPT-5 (API, low/high effort), Gemini 3 Pro Preview, and Meerkat in zero-shot settings, though trailing Gemini 2.5 Pro. ICL leads to improved performance on a case-by-case basis, allowing Llama 3 and Qwen2.5 to match Gemini 2.5 Pro in binary classification. Systematic lexical-ablation experiments show that SLM decisions are often grounded in valid scientific cues but can be influenced by spurious textual artifacts, underscoring need for interpretability in high-stakes pipelines. Our results reveal both promise and limitations of modern SLMs for scientific triage; pairing SLMs with simple but principled prompting strategies can approach performance of the strongest LLMs for targeted literature filtering in co-scientist pipelines.
title Small Language Models Can Use Nuanced Reasoning For Health Science Research Classification: A Microbial-Oncogenesis Case Study
topic Computational Engineering, Finance, and Science
Quantitative Methods
url https://arxiv.org/abs/2512.06502