MetninOzU at BioLaySumm2025: Text Summarization with Reverse Data Augmentation and Injecting Salient Sentences

In this paper, we present our approach to the BioLaySumm 2025 Shared Task on lay summarization of biomedical research articles, which was conducted as part of the BioNLP Workshop 2025.This marks the third edition of the BioLaySumm Shared Task (Goldsack et al., 2023(Goldsack et al., , 2024;;Xiao et al., 2025).The aim of the task is to create lay summaries from scientific articles to improve accessibility for a nonexpert audience.To this end, we applied preprocessing techniques to clean and standardize the input texts, and fine-tuned Qwen2.5 (Team, 2024; Team) and Qwen3-based language models (Yang et al., 2025;Team, 2025) for the summarization task.For abstract-based finetuning, we investigated whether we can insert salient sentences from the main article into the summary to enrich the input.We also curated a dataset of child-friendly articles with corresponding gold-standard summaries and used large language models to rewrite them into more complex scientific variants to augment our training data with more examples.