Newest papers

EpiLens: Lightweight RAG for Epidemiological Knowledge Acquisition

Vincenzo Perri, Ciro Cattuto, Daniela Paolotti · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26730 · cited by 0 works (OpenAlex) · open-access PDF

Chinese

为了为未来的 SAR 爆发做准备,研究人员需要知道已经做过的研究和他们使用的数据。手动地图的大型文献是慢的,而单独的大型语言模型可以混淆或混淆来源。我们介绍了 EpiLens,一个轻量级的,开源检索增加的生成工作流程,它将固定的检索模板和输出方案应用于每篇论文中,并将输出链接到来源通道。我们从多病原体参数研究的来源中构建了 2,297 篇论文,并评估了 EpiLens 的纸质分类工作流程,与 214 篇手动标签的论文相比。 没有任务特定的培训数据,分类器在四个任务中匹配或超过了测试的监督和零图基线。 研究

Machine translation (Meta M2M100); the English original follows.

Abstract

To prepare for future outbreaks, researchers need to know what studies have been done and what data they use. Mapping a large literature by hand is slow, while large language models alone can misstate or conflate sources. We present EpiLens, a lightweight, open-source retrieval-augmented generation package that applies a fixed retrieval template and output schema to every paper in a corpus and links outputs to source passages. We build a corpus of 2,297 papers from the sources of a multi-pathogen parameter study and evaluate EpiLens's paper-classification workflow against 214 manually labelled papers. Without task-specific training data, the classifier matches or exceeds the tested supervised and zero-shot baselines across four tasks. The study's early extraction sheets cite published sources for 327 estimates. We link each estimate to a cited document or to corpus studies included by a review. Then, we use the classifier's labels to compare the papers associated with different parameters and pathogens. EpiLens labels more papers linked to reproduction numbers than fatality risks as model-based (54% versus 22%, compared with 62% versus 24% in the manual labels). The gap is consistent with the frequent use of transmission models to estimate reproduction numbers and persists within each of five pathogens compared. Beyond the contrast between parameters, the model-based share of papers linked to incubation-period estimates differs by pathogen: 55% for SARS-CoV-2 versus 6% for mpox.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Workflow, Classifier (UML), Artificial intelligence, Schema (genetic algorithms), Training set

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange