# A Human-in-the-Loop Corpus for LLM-Based Simplification of Scientific Summaries

arXiv: https://arxiv.org/abs/2607.25630 · HTML: https://mlsanity.com/paper/2607.25630/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 18 references that are in the map.
- First posted on arXiv 28 Jul 2026.

## Builds on (most cited first, 8 of 8)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [BLEU is Not Suitable for the Evaluation of Text Simplification](https://mlsanity.com/paper/1810.05995/) (2018)
- [ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation Networks](https://mlsanity.com/paper/1909.01716/) (2019)
- [Redefining Simplicity: Benchmarking Large Language Models from Lexical to Document Simplification](https://mlsanity.com/paper/2502.08281/) (2025)
- [LLM-based Text Simplification and its Effect on User Comprehension and Cognitive Load](https://mlsanity.com/paper/2505.01980/) (2025)
- [Text Simplification of Scientific Texts for Non-Expert Readers](https://mlsanity.com/paper/2307.03569/) (2023)
- [Collaboration in the Time of COVID: A Scientometric Analysis of Multidisciplinary SARS-CoV-2 Research](https://mlsanity.com/paper/2108.13370/) (2021)

## Abstract (arXiv)

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.