mlsanityData to 7 Oct 2026

Comparing human and LLM proofreading in L2 writing: Impact on lexical and syntactic features

arXiv 2506.09021 ↗First posted 10 Jun 2025cs.CLcited by 2

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 6 of its 50 references that are in the map. First posted on arXiv 10 Jun 2025.

Builds on

6 of 50 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023LLaMA: Open and Efficient Foundation Language Models27 Feb

Other references · 5

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2023Is ChatGPT a Highly Fluent Grammatical Error Correction System? A Comprehensive Evaluationcited by 97
  3. 2023ChatGPT or Grammarly? Evaluating ChatGPT on Grammatical Error Correction Benchmarkcited by 77
  4. 2023LLM-as-a-tutor in EFL Writing Education: Focusing on Evaluation of Student-LLM Interactioncited by 28
  5. 2024GPT-3.5 for Grammatical Error Correctioncited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026The Crutch or the Ceiling? How Different Generations of LLMs Shape EFL Student Writingscited by 0
  2. 2026Incentives Of EdTech: A Systematic Review Of EduNLP Researchcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Can AI writing be salvaged? Mitigating Idiosyncrasies and Improving Human-AI Alignment in the Writing Process through Edits
  2. 2026How Robust Is Multimodal Claim Verification to LLM Rewriting?
  3. 2026Individual and Combined Effects of English as a Second Language and Typos on LLM Performance
  4. 2026More Aligned, Less Diverse? Analyzing the Grammar and Lexicon of Two Generations of LLMs
  5. 2025Evaluating Robustness of Large Language Models Against Multilingual Typographical Errors
  6. 2025Word Overuse and Alignment in Large Language Models: The Influence of Learning from Human Feedback
  7. 2025LMR-BENCH: Evaluating LLM Agent's Ability on Reproducing Language Modeling Research
  8. 2025Psycholinguistic Word Features: a New Approach for the Evaluation of LLMs Alignment with Humans