Saved in:
Bibliographic Details
Main Authors: Qiang, Jipeng, Huang, Minjiang, Zhu, Yi, Yuan, Yunhao, Zhang, Chaowei, Ouyang, Xiaoye
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.15268
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913666584018944
author Qiang, Jipeng
Huang, Minjiang
Zhu, Yi
Yuan, Yunhao
Zhang, Chaowei
Ouyang, Xiaoye
author_facet Qiang, Jipeng
Huang, Minjiang
Zhu, Yi
Yuan, Yunhao
Zhang, Chaowei
Ouyang, Xiaoye
contents Lexical Simplification (LS) methods use a three-step pipeline: complex word identification, substitute generation, and substitute ranking, each with separate evaluation datasets. We found large language models (LLMs) can simplify sentences directly with a single prompt, bypassing the traditional pipeline. However, existing LS datasets are not suitable for evaluating these LLM-generated simplified sentences, as they focus on providing substitutes for single complex words without identifying all complex words in a sentence. To address this gap, we propose a new annotation method for constructing an all-in-one LS dataset through human-machine collaboration. Automated methods generate a pool of potential substitutes, which human annotators then assess, suggesting additional alternatives as needed. Additionally, we explore LLM-based methods with single prompts, in-context learning, and chain-of-thought techniques. We introduce a multi-LLMs collaboration approach to simulate each step of the LS task. Experimental results demonstrate that LS based on multi-LLMs approaches significantly outperforms existing baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2501_15268
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle New Evaluation Paradigm for Lexical Simplification
Qiang, Jipeng
Huang, Minjiang
Zhu, Yi
Yuan, Yunhao
Zhang, Chaowei
Ouyang, Xiaoye
Computation and Language
Lexical Simplification (LS) methods use a three-step pipeline: complex word identification, substitute generation, and substitute ranking, each with separate evaluation datasets. We found large language models (LLMs) can simplify sentences directly with a single prompt, bypassing the traditional pipeline. However, existing LS datasets are not suitable for evaluating these LLM-generated simplified sentences, as they focus on providing substitutes for single complex words without identifying all complex words in a sentence. To address this gap, we propose a new annotation method for constructing an all-in-one LS dataset through human-machine collaboration. Automated methods generate a pool of potential substitutes, which human annotators then assess, suggesting additional alternatives as needed. Additionally, we explore LLM-based methods with single prompts, in-context learning, and chain-of-thought techniques. We introduce a multi-LLMs collaboration approach to simulate each step of the LS task. Experimental results demonstrate that LS based on multi-LLMs approaches significantly outperforms existing baselines.
title New Evaluation Paradigm for Lexical Simplification
topic Computation and Language
url https://arxiv.org/abs/2501.15268