.png){kind=icon}
返回
Progressive Document-level Text Simplification via Large Language Models
.png){kind=icon}
PRE
AI
DOI：10.1007/s00354-025-00309-1.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Research on text simplification has primarily focused on lexical and sentence-level changes. Long document-level simplification (DS) is still relatively unexplored. Large Language Models (LLMs), like ChatGPT, have excelled in many natural language processing tasks. However, their performance on DS tasks is unsatisfactory, as they often treat DS as merely document summarization. For the DS task, the generated long sequences not only must maintain consistency with the original document throughout, but complete moderate simplification operations encompassing discourses, sentences, and word-level simplifications. Human editors employ a hierarchical complexity simplification strategy to simplify documents. This study delves into simulating this strategy through the utilization of a multi-stage collaboration using LLMs. We propose a progressive simplification method (ProgDS) by hierarchically decomposing the task, including the discourse-level, topic-level, and lexical-level simplification. Experimental results demonstrate that ProgDS significantly outperforms existing smaller models or direct prompting with LLMs, advancing the state-of-the-art in the document simplification task.
Keyword:
Document Simplification
Large Language Model
ChatGPT
Multi-stage System
Text Generation
期刊
N
IF:
2.8
论文数:
24
被引数:
652
机构
引用论文
MobileRaT: A Lightweight Radio Transformer Method for Automatic Modulation Classification in Drone Communication SystemsMobileRaT: 一种用于无人机通信系统中自动调制分类的轻量级无线电变压器方法.png)
DRONES
OAAI
DRONESIF4.8
OAAI分享收藏分享收藏
查看更多内容