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

German

Um sich auf zukünftige SAR-Ausbrüche vorzubereiten, müssen Forscher wissen, welche Studien getan wurden und welche Daten sie verwenden. Die Kartierung einer großen Literatur von Hand ist langsam, während große Sprachmodelle allein Quellen verwechseln oder verwechseln können. Wir präsentieren EpiLens, ein leichtes, open-source-recovery-vergrößertes Generation-Workflow-Paket, das eine feste Recovery-Vorlage und ein Output-Schema auf jedes Papier in einem Corpus anwendet und Verbindungen zu Quellpassagen herstellt. Wir bauen ein Corpus von 2.297 Papieren aus den Quellen einer Multi-Pathogen-Parameter-Studie und bewerten den Papier-Klassifizierungs-Workflow von EpiLens gegenüber 214 manuell

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