# ReLay: Personalized LLM-Generated Plain-Language Summaries for Better Understanding, but at What Cost?

arXiv: https://arxiv.org/abs/2605.00468 · HTML: https://mlsanity.com/paper/2605.00468/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 62 references that are in the map.
- First posted on arXiv 1 May 2026.

## Builds on (most cited first, 27 of 27)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [GoEmotions: A Dataset of Fine-Grained Emotions](https://mlsanity.com/paper/2005.00547/) (2020)
- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [MedCPT: Contrastive Pre-trained Transformers with Large-scale PubMed Search Logs for Zero-shot Biomedical Information Retrieval](https://mlsanity.com/paper/2307.00589/) (2023)
- [Medical Hallucinations in Foundation Models and Their Impact on Healthcare](https://mlsanity.com/paper/2503.05777/) (2025)
- [Conversational Health Agents: A Personalized LLM-Powered Agent Framework](https://mlsanity.com/paper/2310.02374/) (2023)
- [When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunities](https://mlsanity.com/paper/2307.16376/) (2023)
- [Bias in Large Language Models: Origin, Evaluation, and Mitigation](https://mlsanity.com/paper/2411.10915/) (2024)
- [Health-LLM: Large Language Models for Health Prediction via Wearable Sensor Data](https://mlsanity.com/paper/2401.06866/) (2024)
- [Improving Retrieval-Augmented Generation in Medicine with Iterative Follow-up Questions](https://mlsanity.com/paper/2408.00727/) (2024)
- [Personalized Large Language Models](https://mlsanity.com/paper/2402.09269/) (2024)
- [GPTCoach: Towards LLM-Based Physical Activity Coaching](https://mlsanity.com/paper/2405.06061/) (2024)
- [ChatDiet: Empowering Personalized Nutrition-Oriented Food Recommender Chatbots through an LLM-Augmented Framework](https://mlsanity.com/paper/2403.00781/) (2024)
- [APPLS: Evaluating Evaluation Metrics for Plain Language Summarization](https://mlsanity.com/paper/2305.14341/) (2023)
- [Personalized Jargon Identification for Enhanced Interdisciplinary Communication](https://mlsanity.com/paper/2311.09481/) (2023)
- [ReadCtrl: Personalizing text generation with readability-controlled instruction learning](https://mlsanity.com/paper/2406.09205/) (2024)
- [MirrorStories: Reflecting Diversity through Personalized Narrative Generation with Large Language Models](https://mlsanity.com/paper/2409.13935/) (2024)
- [PrLM: Learning Explicit Reasoning for Personalized RAG via Contrastive Reward Optimization](https://mlsanity.com/paper/2508.07342/) (2025)
- [Steering AI-Driven Personalization of Scientific Text for General Audiences](https://mlsanity.com/paper/2411.09969/) (2024)
- [Whose story is it? Personalizing story generation by inferring author styles](https://mlsanity.com/paper/2502.13028/) (2025)
- [PlainQAFact: Retrieval-augmented Factual Consistency Evaluation Metric for Biomedical Plain Language Summarization](https://mlsanity.com/paper/2503.08890/) (2025)
- [BiasGuard: A Reasoning-enhanced Bias Detection Tool For Large Language Models](https://mlsanity.com/paper/2504.21299/) (2025)
- [Improving RAG for Personalization with Author Features and Contrastive Examples](https://mlsanity.com/paper/2504.08745/) (2025)
- [Are LLM-generated plain language summaries truly understandable? A large-scale crowdsourced evaluation](https://mlsanity.com/paper/2505.10409/) (2025)

## Abstract (arXiv)

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. Personalization improves comprehension and perceived quality, but it also raises the risk of reinforcing user biases and introducing hallucinations, revealing a trade-off between personalization and safety. These findings highlight the need for personalization methods that are both effective and trustworthy for diverse lay audiences.