dissertation · 2025

SciGrade: A Multi-Grade Scientific Text Simplification and Readability Dataset.

Khan, Fatimah Lyba

Cited by 0Open access

Abstract

This thesis investigates the use of Large Language Models (LLMs) for scientific text simplification, aiming to enhance accessibility across various educational levels while maintaining scientific accuracy. It addresses the challenge of simplifying complex scientific texts for a wide audience, including students, professionals, and the general public. A key component is the development of SciGrade, a multigrade dataset with simplified versions of scientific texts spanning 10 Science fields. This dataset serves as a benchmark for evaluating the performance of small and medium-scale LLMs in the simplification task. The thesis employs a multi-step evaluation framework, combining automated metrics (e.g., SARI, BERTScore, FKGL, FRE), LLM-based assessments, and human annotations. Larger models like Mistral-24B and Qwen-14B excel in similarity, accuracy, and readability. Self-reflection improves coherence and precision, offering scalable solutions for scientific communication. This work contributes to the advancement of AI-driven text simplification, with im plications for education, crossdisciplinary research, and public science communication, facilitating wider access to scientific knowledge across diverse audiences.

Cite this paper

APA 7

Khan, F. L. (2025). SciGrade: A Multi-Grade Scientific Text Simplification and Readability Dataset. https://doi.org/10.82419/275

MLA 9

Khan, Fatimah Lyba. “SciGrade: A Multi-Grade Scientific Text Simplification and Readability Dataset.” 2025, https://doi.org/10.82419/275.

Chicago

Khan, Fatimah Lyba. 2025. “SciGrade: A Multi-Grade Scientific Text Simplification and Readability Dataset.” https://doi.org/10.82419/275.

Harvard

Khan, F.L. (2025) ‘SciGrade: A Multi-Grade Scientific Text Simplification and Readability Dataset’. Available at: https://doi.org/10.82419/275.

BibTeX

@phdthesis{khan2025scigrade,
  title = {{SciGrade: A Multi-Grade Scientific Text Simplification and Readability Dataset.}},
  author = {Khan, Fatimah Lyba},
  year = {2025},
  doi = {10.82419/275}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.