Reproduce “LLM-based Text Simplification and its Effect on User Comprehension and Cognitive Load” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Theo Guidroz, Diego Ardila, Jimmy Li, Adam Mansour, Paul Jhun, Nina Gonzalez, Xiang Ji, Mike Sanchez and 18 more
A large-scale randomized controlled study from Google evaluates LLM-based text simplification using Gemini models, demonstrating a 3.9% improvement in comprehension accuracy and reduced cognitive load across multiple domains, with particularly strong gains of 14.6% for medical texts from PubMed.
Key insights
- Text simplification significantly improved comprehension, especially for more difficult questions and medical texts
- Users reported greater confidence and lower cognitive load when reading simplified texts
- Automated evaluation using LLMs enabled effective optimization of the simplification process
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.