Medical systematic reviews can be very costly and resource intensive. We explore how Large Language Models (LLMs) can support and be trained to perform literature screening when provided with a detailed set of selection criteria. Specifically, we instruction tune LLaMA and Guanaco models to perform abstract screening for medical systematic reviews. Our best model, Bio-SIEVE, outperforms both ChatGPT and trained traditional approaches, and generalises better across medical domains. However, there remains the challenge of adapting the model to safety-first scenarios. We also explore the impact of multi-task training with Bio-SIEVE-Multi, including tasks such as PICO extraction and exclusion reasoning, but find that it is unable to match single-task Bio-SIEVE's performance. We see Bio-SIEVE as an important step towards specialising LLMs for the biomedical systematic review process and explore its future developmental opportunities. We release our models, code and a list of DOIs to reconstruct our dataset for reproducibility.
@article{arxiv.2308.06610,
title = {Bio-SIEVE: Exploring Instruction Tuning Large Language Models for Systematic Review Automation},
author = {Ambrose Robinson and William Thorne and Ben P. Wu and Abdullah Pandor and Munira Essat and Mark Stevenson and Xingyi Song},
journal= {arXiv preprint arXiv:2308.06610},
year = {2023}
}