Abstract
Text simplification is crucial for making texts more accessible, yet current research primarily focuses on sentence-level simplification, neglecting document-level simplification and the different reading levels of target audiences. To bridge these gaps, we introduce ExpertEase, a multi-agent framework for grade-specific document simplification using Large Language Models (LLMs). ExpertEase simulates real-world text simplification by introducing expert, teacher, and student agents that cooperate on the task and rely on external tools for calibration. Experiments demonstrate that this multi-agent approach significantly enhances LLMs’ ability to simplify reading materials for diverse audiences. Furthermore, we evaluate the performance of LLMs varying in size and type, and compare LLM-generated texts with human-authored ones, highlighting their potential in educational resource development and guiding future research.- Anthology ID:
- 2024.findings-emnlp.530
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2024
- Month:
- November
- Year:
- 2024
- Address:
- Miami, Florida, USA
- Editors:
- Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 9080–9099
- Language:
- URL:
- https://aclanthology.org/2024.findings-emnlp.530
- DOI:
- 10.18653/v1/2024.findings-emnlp.530
- Cite (ACL):
- Kaijie Mo and Renfen Hu. 2024. ExpertEase: A Multi-Agent Framework for Grade-Specific Document Simplification with Large Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 9080–9099, Miami, Florida, USA. Association for Computational Linguistics.
- Cite (Informal):
- ExpertEase: A Multi-Agent Framework for Grade-Specific Document Simplification with Large Language Models (Mo & Hu, Findings 2024)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2024.findings-emnlp.530.pdf