Exploring sentence-level revision capabilities of large language models in English for academic purposes writing assistance

Salvato in:
Dettagli Bibliografici
Pubblicato in:Asian-Pacific Journal of Second and Foreign Language Education vol. 10, no. 1 (Dec 2025), p. 27
Pubblicazione:
Springer Nature B.V.
Soggetti:
Accesso online:Citation/Abstract
Full Text - PDF
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!

MARC

LEADER 00000nab a2200000uu 4500
001 3212989461
003 UK-CbPIL
022 |a 2363-5169 
024 7 |a 10.1186/s40862-025-00334-z  |2 doi 
035 |a 3212989461 
045 2 |b d20251201  |b d20251231 
245 1 |a Exploring sentence-level revision capabilities of large language models in English for academic purposes writing assistance 
260 |b Springer Nature B.V.  |c Dec 2025 
513 |a Journal Article 
520 3 |a The English for Academic Purposes (EAP) is pivotal for scholarly communication; however, it poses significant challenges for non-native English speakers. Recently, Large Language Models (LLMs) have been extensively utilized in EAP to assist with writing tasks. EAP writing assistance typically encompasses several downstream tasks in natural language processing, such as Grammatical Error Correction (GEC). Nonetheless, some studies have revealed that the performance of LLMs in GEC tasks is inferior to traditional GEC solutions. To explore the capabilities of LLMs more thoroughly in aspects like deep semantic and syntactic structures, this study aims to rigorously assess the performance of LLMs in the Sentence-level Revision (SentRev) task. We designed three sets of meticulous experiments to evaluate the efficacy of different LLMs. The first experiment assessed LLMs using prompts in ten different languages, finding that the SentRev performance of LLMs was heavily influenced by the language of the prompt and the quality of the input text. The second experiment investigated the performance of English LLMs with minimal prompting in the SentRev task, yet the results showed no significant changes, contradicting some prior studies. In the third experiment, we devised an innovative and straightforward method that significantly enhanced the performance of multiple LLMs by integrating academic phrases from the Formulaic Language Academic Phrasebank&#xa0;(<ext-link xlink:href="https://www.phrasebank.manchester.ac.uk/" ext-link-type="uri">https://www.phrasebank.manchester.ac.uk/</ext-link>), thus overcoming the performance limitations imposed by different languages on LLMs. Additionally, our study highlights the deficiencies in existing evaluation benchmarks and suggests that higher-level, discourse-based EAP text evaluation benchmarks merit deeper exploration. 
653 |a Language 
653 |a Semantics 
653 |a Syntax 
653 |a Syntactic structures 
653 |a Natural language processing 
653 |a Academic writing 
653 |a Academic discourse 
653 |a Language modeling 
653 |a Large language models 
653 |a Scholarly communication 
653 |a Formulaic language 
653 |a English for academic purposes 
653 |a Second language learning 
653 |a Experiments 
653 |a Writing 
653 |a English language 
653 |a Task performance 
653 |a Efficacy 
653 |a Languages 
653 |a Academic achievement 
653 |a Language Processing 
773 0 |t Asian-Pacific Journal of Second and Foreign Language Education  |g vol. 10, no. 1 (Dec 2025), p. 27 
786 0 |d ProQuest  |t Education Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3212989461/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3212989461/fulltextPDF/embedded/6A8EOT78XXH2IG52?source=fedsrch