Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2506.09021 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908588566380544 |
|---|---|
| author | Sung, Hakyung Csuros, Karla Sung, Min-Chang |
| author_facet | Sung, Hakyung Csuros, Karla Sung, Min-Chang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_09021 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Comparing human and LLM proofreading in L2 writing: Impact on lexical and syntactic features Sung, Hakyung Csuros, Karla Sung, Min-Chang Computation and Language 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. |
| title | Comparing human and LLM proofreading in L2 writing: Impact on lexical and syntactic features |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2506.09021 |