EpiLens: Lightweight RAG for Epidemiological Knowledge Acquisition
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.
Related
- A temperature-adaptive logit-standardized knowledge distillation for lightweight network intrusion detection
- High-speed optical comb-based 3D tomographic profiling using Fourier-transform method with reduced-frame acquisition
- Dual Branch Transformer with Physical Priors for PSF Acquisition to Enable PSF Guided Image Restoration against Co Phasing Errors in Optical Synthetic Aperture Interferometric Imaging
- Acquisition-calibrated degradation synthesis and dual-domain reconstruction for accelerated spectral-domain OCT
- A Scalable Two-Stage Back-End Architecture for 400GbE Data Acquisition Systems
BibTeX
@misc{perri2026epilens,
title = {{EpiLens: Lightweight RAG for Epidemiological Knowledge Acquisition}},
author = {Vincenzo Perri and Ciro Cattuto and Daniela Paolotti},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.26730},
eprint = {2610.26730},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.26730},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - EpiLens: Lightweight RAG for Epidemiological Knowledge Acquisition
AU - Vincenzo Perri
AU - Ciro Cattuto
AU - Daniela Paolotti
PY - 2026
DA - 2026/10/19
PB - arXiv
DO - 10.48550/arxiv.2610.26730
UR - https://arxiv.org/abs/2610.26730
AB - 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.
ER -