Tag
This paper presents a human-in-the-loop workflow for creating a corpus of LLM-based simplifications of scientific summaries, using SciSummNet and GPT-4o-mini with non-expert and expert feedback to improve cross-disciplinary accessibility.
This paper investigates how the growing use of LLMs in writing is altering scientific communication, using a corpus of ACL papers and synthetic data to show lexical and stylistic changes, and connects these to subjective reading experience via expert annotations.