对比人类与大模型在二语写作中的修改效果，发现大模型更擅长重构语言表达。
Comparing human and LLM proofreading in L2 writing: Impact on lexical and syntactic features
- 比较人类与三款大模型的修改策略，分析其对词汇与句法的影响。
- 大模型显著提升词汇多样性与修饰词使用，增强句子复杂度。
- 不同大模型修改结果高度一致，适合用于标准化写作润色。
本研究考察了人类与大模型在相同二语写作中对词汇和句法特征的修改干预，旨在提升整体可理解性，并评估三种大模型（ChatGPT-4o、Llama3.1-8b、Deepseek-r1-8b）的输出一致性。结果表明，人类与大模型均能有效提升双词搭配（bigram）词汇特征，可能增强相邻词语间的连贯性与语境衔接。然而，大模型采用更具生成性的修改方式，广泛重写词汇与句式结构，如使用更多样化且复杂的词汇，并在名词短语中引入更多形容词修饰成分。三种大模型在主要词汇与句法特征上的修改结果高度一致。
原文摘要 · Abstract (English)
This study examines the lexical and syntactic interventions of human and LLM proofreading aimed at improving overall intelligibility in identical second language writings, and evaluates the consistency of outcomes across three LLMs (ChatGPT-4o, Llama3.1-8b, Deepseek-r1-8b). Findings show that both human and LLM proofreading enhance bigram lexical features, which may contribute to better coherence and contextual connectedness between adjacent words. However, LLM proofreading exhibits a more generative approach, extensively reworking vocabulary and sentence structures, such as employing more diverse and sophisticated vocabulary and incorporating a greater number of adjective modifiers in noun phrases. The proofreading outcomes are highly consistent in major lexical and syntactic features across the three models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。