BeLink: Biomedical Entity Linking Meets Generative Re-Ranking
For practitioners needing efficient and accurate BEL, this work offers a practical solution that improves accuracy and speed over existing methods.
Biomedical Entity Linking (BEL) with LLMs is computationally inefficient; the authors propose instruction-tuning of open-source generative models for re-ranking, achieving 3%-24% improvement in linking accuracy with reduced inference time.
Despite recent progress, Biomedical Entity Linking (BEL) with large language models (LLMs) remains computationally inefficient and challenging to deploy in practical settings. In this work, we demonstrate that instruction-tuning of open-source generative models can offer an effective solution when applied at the re-ranking stage of the BEL pipeline. We propose a set-wise instruction-tuning formulation that enables fast and accurate candidate selection. Our method demonstrates strong performance on multiple BEL benchmarks, yielding significant improvements in linking accuracy (3%-24%) while reducing inference time compared to the state-of-the-art. We integrate our generative re-ranker into BeLink, a modular, end-to-end system designed for practical real-world BEL applications.