Abstracts produce faster and better easy-to-understand biomedical summaries
Abstracts or full text? Evaluating input scope and computational efficiency in biomedical lay summarization
Computation and Language
Summary
Biomedical research papers are written for experts and often use complicated language that many people find hard to understand. The authors studied whether using just the abstracts (summary sections) of these papers can create easy-to-understand summaries as good as those made from full articles, which take much longer to process. They found that summaries based on abstracts were not only faster to produce but also better overall in quality. They also checked different ways to generate summaries and confirmed that focusing on abstracts saves a lot of computing time without losing accuracy.
What this means in practice
- •For health communication teams: Create quicker, accurate patient-friendly summaries of biomedical research using article abstracts instead of full texts to reduce processing time.
- •For medical information platform developers: Implement abstract-based summarization to lower computational costs while maintaining quality in providing accessible biomedical content to users.
Authors
Egecan Çelik Evgin, İlknur Karadeniz, Olcay Taner Yıldız
Abstract
Biomedical research articles are mainly written for experts and often contain terms that are difficult for the general public to understand. Automated lay summarization has become a solution to make biomedical knowledge easier for patients and the public to understand. However, generating lay summaries from full-text articles requires more computing power because the articles are long and costly to process. Fine-tuning large language models for this task also requires substantial resources. This study asks two questions: (1) whether abstracts contain enough information to produce lay summaries as good as those based on full-text articles, and (2) whether few-shot learning performs as well as task-specific fine-tuning. The study used two public biomedical lay summarization datasets and two recent models, evaluated for readability, factual consistency, semantic similarity, and runtime efficiency. Results show that abstract-based summarization performs better overall. Across both datasets and models, abstract fine-tuning is 4.70 times faster, while abstract zero- and few-shot prompting is 5.31 times faster than full-text methods. These results show that abstract-based prompting reduces runtime cost while maintaining lay summary quality.