TL;DR
The findings have implications for LLM use in science communication and NLG and provide insight on the difficulties of creating operationalizable guidelines for German comprehensible language.
This work study large language model (LLM)-based simplification of scientific texts and presents a human-in-the-loop workflow that transforms expert summaries into more accessible versions for non-specialists.
It was concluded that texts generated by artificial intelligence constitute a separate linguistic phenomenon with its own set of characteristics, which requires a special typology and a flexible, updatable analysis methodology.
A statistically significant increase in lexical density and frequency of cohesive markers has been revealed, indicating an increase in information compression and explicit discursive organization of texts, consistent with characteristics described in AI-assisted writing studies.
It is concluded that adopting LLMs in the public sector demands “Human-in-the-loop” workflows to ensure legal accuracy and clear communication.
Comparing human annotations with outputs from generative large language models and examining their alignment with theoretical models of textuality show how computational approaches can shed light on linguistic theories and, vice versa, how linguistic theories can guide the application of computational resources.
Results from automatic and human evaluations show that fine-tuning on IMPaCTS improves performance both in terms of task completion and adherence to the targeted readability levels compared to few-shot baselines.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
