{"slug": "a-human-in-the-loop-corpus-for-llm-based-simplification-of-scientific-summaries", "title": "A Human-in-the-Loop Corpus for LLM-Based Simplification of Scientific Summaries", "summary": "Researchers released a human-in-the-loop corpus for LLM-based simplification of scientific summaries, finding that GPT-4o-mini-generated summaries were preferred for comprehensibility and simplicity but that expert edits highlighted the need to preserve domain-specific terminology and scientific claims. The corpus, built from SciSummNet with feedback from STEM readers and computer science experts, supports training and benchmarking of simplification systems for cross-disciplinary communication.", "body_md": "arXiv:2607.25630v1 Announce Type: new\nAbstract: Interdisciplinary research is accelerating, yet scientific papers remain difficult to understand outside their home fields. We study large language model (LLM)-based simplification of scientific texts and present a human-in-the-loop workflow that transforms expert summaries into more accessible versions for non-specialists. Using SciSummNet as the source corpus, we first generate baseline simplifications with GPT-4o-mini. In Phase 1, readers from STEM fields outside computer science identify difficult sentences and phrases and compare the original and GPT-simplified summaries in terms of comprehensibility, naturalness, and simplicity. In Phase 2, computer science experts use this feedback to create expert-edited reference simplifications. We release the resulting corpus together with human judgments and automatic evaluation results. The Phase 1 judgments show a clear preference for the GPT-generated summaries in terms of comprehensibility and simplicity, while qualitative analysis of the Phase 2 edits highlights the importance of preserving domain-specific terminology and the strength of scientific claims. The resulting resource supports the training and benchmarking of simplification systems for cross-disciplinary scientific communication.", "url": "https://wpnews.pro/news/a-human-in-the-loop-corpus-for-llm-based-simplification-of-scientific-summaries", "canonical_source": "https://www.machinebrief.com/news/a-human-in-the-loop-corpus-for-llm-based-simplification-of-s-40co", "published_at": "2026-07-29 04:00:00+00:00", "updated_at": "2026-07-29 05:00:14.758038+00:00", "lang": "en", "topics": ["large-language-models", "natural-language-processing", "ai-research"], "entities": ["SciSummNet", "GPT-4o-mini"], "alternates": {"html": "https://wpnews.pro/news/a-human-in-the-loop-corpus-for-llm-based-simplification-of-scientific-summaries", "markdown": "https://wpnews.pro/news/a-human-in-the-loop-corpus-for-llm-based-simplification-of-scientific-summaries.md", "text": "https://wpnews.pro/news/a-human-in-the-loop-corpus-for-llm-based-simplification-of-scientific-summaries.txt", "jsonld": "https://wpnews.pro/news/a-human-in-the-loop-corpus-for-llm-based-simplification-of-scientific-summaries.jsonld"}}