Overview of the BioLaySumm 2024 Shared Task on the Lay Summarization of Biomedical Research Articles

TL;DR

BioLaySumm 2024 reports the second edition of the biomedical lay-summarisation shared task, detailing two datasets (PLOS and eLife), revised evaluation metrics (including LENS, AlignScore, and SummaC), and a new ranking protocol. The event attracted 53 teams and over 200 submissions, marking a large increase from the prior year and revealing a pronounced move toward large language models and retrieval-augmented approaches. The results highlight a trade-off landscape among relevance, readability, and factuality, with several teams surpassing a BART-based baseline and many adopting dataset-specific or unified modeling strategies. The work demonstrates the feasibility and ongoing challenges of automatic lay summarisation for disseminating biomedical research to non-expert audiences, with practical implications for broader access to scientific knowledge.

Abstract

This paper presents the setup and results of the second edition of the BioLaySumm shared task on the Lay Summarisation of Biomedical Research Articles, hosted at the BioNLP Workshop at ACL 2024. In this task edition, we aim to build on the first edition's success by further increasing research interest in this important task and encouraging participants to explore novel approaches that will help advance the state-of-the-art. Encouragingly, we found research interest in the task to be high, with this edition of the task attracting a total of 53 participating teams, a significant increase in engagement from the previous edition. Overall, our results show that a broad range of innovative approaches were adopted by task participants, with a predictable shift towards the use of Large Language Models (LLMs).