arXiv cs.CL· Egecan \c{C}elik Evgin, \.{I}lknur Karadeniz, Olcay Taner Y{\i}ld{\i}z·· 2 天前AI 评分24
摘要还是全文？生物医学通俗摘要的输入范围与计算效率评估
Abstracts or full text? Evaluating input scope and computational efficiency in biomedical lay summarization
AI 导读
一项基于两个公开生物医学通俗摘要数据集和两个近期模型的研究发现，基于摘要的通俗摘要生成整体效果优于全文方法。摘要微调比全文方法快 4.70 倍，摘要零样本和少样本提示则快 5.31 倍，在保持通俗摘要质量的同时降低了运行成本。
正文 · 原文
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.
| Comments: | 26 pages, 2 figures |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.21690 [cs.CL] |
| (or arXiv:2610.21690v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.21690 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Egecan Çelik Evgin [view email]
[v1]
Thu, 15 Oct 2026 11:13:36 UTC (405 KB)
来源：arXiv cs.CL · arxiv.org