Shared Task at Biolaysumm2025 : Extract then summarize approach Augmented with UMLS based Definition Retrieval for Lay Summary generation.

Aaradhya Gupta, Parameswari Krishnamurthy


Abstract
The paper presents a modular, two‐track lay‐summary generation system for biomedical research articles, evaluated on the PLOS and eLife subsets of the BioLaySumm2025 shared task. In Task 1, it extracts salient sentences via an LLM–based chunking and summarization pipeline, then applies iterative rewriting to produce an accessible summary. In Task 2, it augments that summary with UMLS‐sourced definitions identified by a BioBERT NER model, yielding improved readability and factual consistency, at the cost of slight reductions in n‐gram overlap metrics like ROUGE and BLEU.
Anthology ID:
2025.bionlp-share.23
Volume:
BioNLP 2025 Shared Tasks
Month:
August
Year:
2025
Address:
Vienna, Austria
Editors:
Sarvesh Soni, Dina Demner-Fushman
Venues:
BioNLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
185–189
Language:
URL:
https://preview.aclanthology.org/acl25-workshop-ingestion/2025.bionlp-share.23/
DOI:
Bibkey:
Cite (ACL):
Aaradhya Gupta and Parameswari Krishnamurthy. 2025. Shared Task at Biolaysumm2025 : Extract then summarize approach Augmented with UMLS based Definition Retrieval for Lay Summary generation.. In BioNLP 2025 Shared Tasks, pages 185–189, Vienna, Austria. Association for Computational Linguistics.
Cite (Informal):
Shared Task at Biolaysumm2025 : Extract then summarize approach Augmented with UMLS based Definition Retrieval for Lay Summary generation. (Gupta & Krishnamurthy, BioNLP 2025)
Copy Citation:
PDF:
https://preview.aclanthology.org/acl25-workshop-ingestion/2025.bionlp-share.23.pdf