analiza aiqbench
This article introduces PlainMedScale, a new corpus designed to evaluate large language models on multi-level medical text comprehensibility in German and English. The research demonstrates that current readability metrics often fail across this gradient and reveals limitations when prompting state-of-the-art open-weight LLMs for plain language generation.
PlainMedScale: A Corpus of Multi-Level Simplified Medical Texts in German and English
arXiv:2608.01158v1 Announce Type: new Abstract: We introduce PlainMedScale, a topic-aligned medical corpus spanning four levels of comprehensibility in German and English, drawn from MSD (professional and consumer), Gesund.Bund, Apotheken Umschau Einfache Sprache, and the NHS. The four tiers correspond to distinct communicative functions --- reference, explanation, decision support, and access --- and move beyond the binary expert--lay contrast of prior corpora. In two pilot studies enabled by the alignments, we show that many readability metrics established on two registers fail to generalize across the full gradient, and that a SOTA open-weight LLM prompted for Plain Language still partially preserves the difficulty of its input. Code (https://github.com/GS-Uni-Heidelberg/PlainMedScale) and data (https://doi.org/10.5281/zenodo.21728290) are made available.
Abstract:We introduce PlainMedScale, a topic-aligned medical corpus spanning four levels of comprehensibility in German and English, drawn from MSD (professional and consumer), this http URL, Apotheken Umschau Einfache Sprache, and the NHS. The four tiers correspond to distinct communicative functions --- reference, explanation, decision support, and access --- and move beyond the binary expert--lay contrast of prior corpora. In two pilot studies enabled by the alignments, we show that many readability metrics established on two registers fail to generalize across the full gradient, and that a SOTA open-weight LLM prompted for Plain Language still partially preserves the difficulty of its input. Code (this https URL) and data (this https URL) are made available.
Computation and Language (cs.CL)
arXiv:2608.01158 [cs.CL]
(or arXiv:2608.01158v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2608.01158 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 208 cuvinte
Subiecte conexe

Presentation: Automating the Web With MCP: Infra That Doesn’t Break
InfoQ · 16 iun. 2026

NVIDIA GTC Taipei at COMPUTEX: Live Updates on What’s Next in AI
NVIDIA · 21 mai 2026
Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers
Hugging Face · 26 aug. 2026
MedVL-SAM2: A unified 3D medical vision-language model for multimodal reasoning and prompt-driven segmentation
arXiv · 2 oct. 2026