ReadFact: A Workflow Framework for Readability and Factual Consistency in Medical Text Simplification
Journal of Computer Science and Artificial Intelligence · 29.05.2026 · 7 (2) · 11-19
DOI: 10.54097/94ns3t96 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Computer Science and Artificial Intelligence, online erschienen am 29.05.2026. Verfasst von Kexin Weng. Die Arbeit nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Biomedical literature often remains inaccessible to lay readers due to technical complexity. Medical text simplification (MTS) aims to improve readability while preserving factual accuracy. We propose ReadFact, a workflow that integrates three complementary components: (i) a simplifier trained with Direct Preference Optimization (DPO), (ii) a readability reward model trained with Proximal Policy Optimization (PPO), and (iii) a PICO-based fact checker for structured factual alignment. Our system is trained on the Cochrane Database of Systematic Reviews. Intermediate simplifications are first generated using DeepSeek-V3, and each (source, mid, target) triple is expanded into preference pairs to supervise both DPO and PPO training. Factual consistency is evaluated using SciBERT-based PICO similarity, while readability is optimized through preference-driven learning. Experiments show that ReadFact improves factual consistency by more than 23% over the DPO baseline and increases readability by over 5 percent. On the NapSS benchmark, ReadFact-DPO achieves the highest BERTScore, demonstrating closer alignment with human references.
Zitieren
APA
Weng, K. (2026). ReadFact: A Workflow Framework for Readability and Factual Consistency in Medical Text Simplification. Journal of Computer Science and Artificial Intelligence, 7(2), 11-19. https://doi.org/10.54097/94ns3t96
Vancouver
Weng K. ReadFact: A Workflow Framework for Readability and Factual Consistency in Medical Text Simplification. Journal of Computer Science and Artificial Intelligence. 2026;7(2):11-19. doi:10.54097/94ns3t96
BibTeX
@article{Weng2026,
author = {Weng, Kexin},
title = {ReadFact: A Workflow Framework for Readability and Factual Consistency in Medical Text Simplification},
journal = {Journal of Computer Science and Artificial Intelligence},
year = {2026},
volume = {7},
number = {2},
pages = {11--19},
doi = {10.54097/94ns3t96}
}
EUVIMED