cs.CL提交于 2026-10-16已译

摘要还是全文？评估生物医学通俗摘要生成的输入范围与计算效率

Abstracts or full text? Evaluating input scope and computational efficiency in biomedical lay summarization

Egecan \c{C}elik Evgin · \.{I}lknur Karadeniz · Olcay Taner Y{\i}ld{\i}z

中文摘要

生物医学研究文章通常面向专家，包含公众难以理解的术语。自动通俗摘要生成旨在降低患者和公众理解生物医学知识的门槛。然而，基于全文生成摘要因文章篇幅长而消耗大量算力，微调大语言模型也需要显著资源。本研究探讨两个问题：摘要是否包含足够信息以生成媲美全文的通俗摘要，以及少样本学习是否表现优于任务特定微调。研究使用两个公开生物医学通俗摘要数据集和两个近期模型，评估可读性、事实一致性、语义相似度和运行效率。结果显示，基于摘要的摘要生成整体表现更优。在两个数据集和模型中，摘要微调比全文方法快 4.70 倍，摘要零样本和少样本提示比全文方法快 5.31 倍。结果表明，基于摘要的提示在保持通俗摘要质量的同时降低了运行时成本。

关键要点

01指出基于全文生成生物医学通俗摘要存在高算力消耗和微调资源需求大的问题。
02对比评估了摘要与全文作为输入，以及少样本学习与微调在通俗摘要生成中的表现。
03实验发现基于摘要的方法在可读性、事实一致性等指标上整体优于基于全文的方法。
04摘要微调比全文方法快 4.70 倍，摘要零样本和少样本提示比全文方法快 5.31 倍。

解读

尚无解读。

原始英文摘要

arXiv:2610.21690v1 Announce Type: new 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.