Alexandra Lee

Plain Language Summaries (PLS) aim to make research accessible to lay readers, but they are typically written in a one-size-fits-all style that ignores differences in readers' information needs and comprehension. In health contexts, this limitation is particularly important because misunderstanding scientific information can affect real-world decisions. Large language models (LLMs) offer new opportunities for personalizing PLS, but it remains unclear whether personalization helps, which strategies are most effective, and how to balance personalization with safety. We introduce **ReLay**, a dataset of 300 participant–PLS pairs from 50 lay participants in both **static** (expert-written) and **interactive** (LLM-personalized) settings. ReLay includes user characteristics, health information needs, information-seeking behavior, comprehension outcomes, interaction logs, and quality ratings. We use ReLay to evaluate five LLMs across two personalization methods: **profile-based prompting**, which conditions generation on participant survey profiles, and **retrieval-based prompting**, which incorporates prior interactions from the same or similar users. The interactive personalized setting yields higher comprehension and perceived quality than the static expert-written setting, while personalization methods can also increase the risk of reinforcing user biases and introducing hallucinations, revealing a trade-off between effectiveness and safety. These findings highlight the need for personalization methods that are both effective and trustworthy for diverse lay audiences.