Your new experience awaits. Try the new design now and help us make it even better

ORIGINAL RESEARCH article

Front. Public Health

Sec. Digital Public Health

Volume 13 - 2025 | doi: 10.3389/fpubh.2025.1619274

This article is part of the Research TopicEthical Considerations of Large Language Models: Challenges and Best PracticesView all 4 articles

HEAL-Summ: A Lightweight and Ethical Framework for Accessible Summarization of Health Information

Provisionally accepted
  • 1York University, Toronto, Canada
  • 2University of Kansas, Lawrence, Kansas, United States

The final, formatted version of the article will be published soon.

The growing volume and complexity of health-related news presents significant barriers to public understanding. While large language models (LLMs) offer a promising means of summarizing such content, many approaches are computationally expensive and can lack sufficient evaluation of ethical as well as representational quality. To address these limitations, this research proposes a lightweight framework called HEAL-Summ (Health Ethics \& Accessibility with Lightweight Summarization) for summarizing Canadian health news articles using LLMs. In the demonstrated instance, the following three models are used: Phi 3, Qwen 2.5, and Llama 3.2. Unlike conventional summarization systems, this approach integrates multi-dimensional evaluation to assess semantic consistency, readability, lexical diversity, emotional alignment, and toxicity. Comparative analyses shows consistent semantic agreement across models, with Phi yielding more accessible summaries and Qwen producing greater emotional as well as lexical diversity. This work goes beyond single-model summarization by providing a structured and ethical framework for longitudinal news analysis, emphasizing low-resource deployment and built-in automated evaluations. The findings highlight the potential for lightweight LLMs to facilitate transparent and emotionally sensitive communication in public health, while maintaining a balance between linguistic expressiveness and ethical reliability. The proposed framework offers a scalable path forward for improving access to complex health information in resource-constrained or high-stakes environments.

Keywords: Health Communication, Large language models, News summarization, semantic evaluation, Information accessibility

Received: 01 May 2025; Accepted: 05 Sep 2025.

Copyright: © 2025 Fisher, Srinivasan, Hillier and Mago. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence: Andrew Fisher, York University, Toronto, Canada

Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.