MIRAGES at BioLaySumm2025: The Impact of Search Terms and Data Curation for Biomedical Lay Summarization
Year: 2025
Type: conference-paper
Abstract: Biomedical articles are often inaccessible to non-experts due to their technical complexity.To improve readability and factuality of lay summaries, we built on an extract-thensummarize framework by experimenting with novel extractive summarization strategies and employing Low Rank Adaptation (LoRA) finetuning of Meta-Llama-3-8B-Instruct on data selected by these strategies.We also explored counterfactual data augmentation and postprocessing definition insertion to further enhance factual grounding and accessibility.Our best performing system treats the article's title and keywords (i.e.search terms) as a single semantic centroid and ranks sentences by their semantic similarity to this centroid.This constrained selection of data serves as input for fine-tuning, achieving marked improvements in readability and factuality of downstream abstractive summaries while maintaining relevance.Our approach highlights the importance of quality data curation for biomedical lay summarization, resulting in 4th best overall performance and 2nd best Readability performance for the BioLaySumm 2025 Shared Task at BioNLP 2025.
Authors: Benjamin Pong, J u - H u i Chen, Jonathan Jiang, Abimael Jimenez, Melody Vahadi
Institution: University of Washington
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4412889071