Top
Women working on a large machine

A Corpus Linguistic Perspective on Error Detection and Correction in English Academic Texts: There’s an AI for That?

Authors

Files

Deckert_2026_AI-Linguistica

Abstract

Students and researchers from various fields of study and from different language backgrounds use English as a lingua franca when writing academic texts. However, even advanced and proficient users continue to make errors (Lennon 1991; Uzuner 2008). Therefore, the arrival of new AI writing tools might seem like the ideal solution, especially for non-native users of English struggling with writing academic texts. The goal of this study is to provide an overview of how useful AI tools can be for error correction purposes from a linguistic perspective. A representative selection of typical German learner errors from different linguistic problem areas was identified using a corpus linguistic approach. Nine AI tools were used to correct fictitious learner texts containing these errors and results indicate notable discrepancies in terms of the tools’ detection accuracy and correction suitability. Critical evaluation of AI applications is one aspect of AI literacy (D. T. K. Ng et al. 2021, OECD 2025), a future skill needed to use these technologies responsibly and competently. This paper provides a basis for further research in this rapidly developing field and offers practical insights for users of English who wish to leverage AI tools as artificial proofreaders for their academic texts.

Deckert_2026_AI-Linguistica

References

Alexander, Louis George. 1994. Right word, wrong word: Words and structures confused and misused by learners of English. Harlow: Longman Group UK Limited.

Amano, Tatsuya & Ramírez-Castañeda, Valeria & Berdejo-Espinola, Violeta & Borokini, Israel & Chowdhury, Shawan & Golivets, Marina & González-Trujillo, Juan David & Montaño-Centellas, Flavia & Paudel, Kumar & White, Rachel Louise et al. 2023. The manifold costs of being a non-native English speaker in science. PLoS Biology 21(7). https://doi.org/10.1371/journal.pbio.3002184

Ammon, Ulrich. 1996. The European Union (EU – formerly European Community): Status change of English during the last fifty years. In Fishman, Joshua A. & Conrad, Andrew W. & Rubal-Lopez, Alma (eds.), Post-Imperial English, 241–268. Berlin, New York: Mouton De Gruyter. https://doi.org/10.1515/9783110872187.241

Baumann, Andreas & Mühlenbernd, Roland. 2022. Less of the same: Modeling horror aequi and extravagance as mechanisms of negative frequency dependence in linguistic diversification. In Ravignani, Andrea & Asano, Rie & Valente, Daria & Ferretti, Francesco & Hartmann, Stefan & Hayashi, Misato & Jadoul, Yannick & Martins, Mauricio & Oseki, Yohei & Rodrigues, Evelina D. et al. (eds.), The evolution of language: Proceedings of the joint conference on language evolution (JCoLE), 50–57. Nijmegen: Joint Conference on Language Evolution (JCoLE). https://doi.org/10.17617/2.3398549

Bo, Zhou & Pek, Lim Seong & Jian, Li & Cong, Wang & Nan, Lu Tian. 2025. The use of artificial intelligence tools in English academic writing among university students: A scoping review. Language Teaching Research Quarterly 53, 95–114. https://doi.org/10.32038/ltrq.2025.53.05

Bowen, José Antonia & Watson, C. Edward. 2024. Teaching with AI: A practical guide to a new era of human learning. Baltimore: Johns Hopkins University Press. https://doi.org/10.56021/9781421449227

Bridle, Marcus. 2019. Learner use of a corpus as a reference tool in error correction: Factors influencing consultation and success. Journal of English for Academic Purposes 37, 52-69. https://doi.org/10.1016/j.jeap.2018.11.003

Brown, Tom B. & Mann, Benjamin & Ryder, Nick & Subbiah, Melanie & Kaplan, Jared & Dhariwal, Prafulla & Neelakantan, Arvind & Shyam, Pranav & Sastry, Girish & Askell, Amanda et al. 2020. Language models are few-shot learners. arXiv. https://doi.org/10.48550/arXiv.2005.14165

Buck, Isabella. 2025. Wissenschaftliches Schreiben mit KI. Tübingen: UVK Verlag. https://doi.org/10.36198/9783838563657

Cengiz, Behice Ceyda & Bilki, Zeynep & Ataş, Amine Hatun & Celik, Berkan. 2025. Exploring second language writers’ engagement with ChatGPT feedback: Revision behaviors and perceptions. System 134. https://doi.org/10.1016/j.system.2025.103837

Clarke, Roger. 2023. The re-conception of AI: Beyond artificial, and beyond intelligence. IEEE Transactions on Technology and Society 4(1), 24–33. https://doi.org/10.1109/TTS.2023.3234051

Coyne, Steven & Sakaguchi, Keisuke & Galvan-Sosa, Diana & Zock, Michael & Inui, Kentaro. 2023. Analyzing the performance of GPT-3.5 and GPT-4 in grammatical error correction. arXiv.

https://doi.org/10.48550/arXiv.2303.14342

Crossley, Scott A. & Bradfield, Franklin & Bustamente, Analynn. 2019. Using human judgments to examine the validity of automated grammar, syntax, and mechanical errors in writing. Journal of Writing Research 11(2), 251–270. https://doi.org/10.17239/jowr-2019.11.02.01

Cummings, Robert E. & Monroe, Stephen M. & Watkins, Marc. 2024. Generative AI in first-year writing: An early analysis of affordances, limitations, and a framework for the future. Computers and Composition 71. https://doi.org/10.1016/j.compcom.2024.102827

Curry, Mary Jane & Lillis, Theresa. 2007. The dominance of English in global scholarly publishing. International Higher Education 46, 6–7. https://doi.org/10.6017/ihe.2007.46.7948

Davies, Mark. 2004. British National Corpus (BNC) (from Oxford University Press). https://www.english-corpora.org/bnc/

Davies, Mark. 2008-. The Corpus of Contemporary American English (COCA). https://www.english-corpora.org/coca/

Davies, Mark. 2013. Corpus of Global Web-Based English (GloWbE). https://www.english-corpora.org/glowbe/

Dolgova, Natalia & Mueller, Charles. 2019. How useful are corpus tools for error correction? Insights from learner data. Journal of English for Academic Purposes 39, 97–108. https://doi.org/10.1016/j.jeap.2019.03.007

Fang, Tao & Yang, Shu & Lan, Kaixin & Wong, Derek F. & Hu, Jinpeng & Chao, Lidia S. & Zhang, Yue. 2023. Is ChatGPT a highly fluent grammatical error correction system? A comprehensive evaluation. arXiv. https://doi.org/10.48550/arXiv.2304.01746

Fitikides, Timothy J. 2002. Common mistakes in English with exercises. 6th edn. Harlow: Pearson Education Limited.

Flowerdew, John. 1999a. Writing for scholarly publication in English: The case of Hong Kong. Journal of Second Language Writing 8(2), 123–145. https://doi.org/10.1016/S1060-3743(99)80125-8

Flowerdew, John. 1999b. Problems in writing for scholarly publication in English: The case of Hong Kong. Journal of Second Language Writing 8(3), 243–264. https://doi.org/10.1016/S1060-3743(99)80116-7

Flowerdew, John. 2008. Scholarly writers who use English as an additional language: What can Goffman’s “stigma” tell us? Journal of English for Academic Purposes 7(2), 77–86. https://doi.org/10.1016/j.jeap.2008.03.002

Flowerdew, John. 2019. The linguistic disadvantage of scholars who write in English as an additional language: Myth or reality. Language Teaching 52(2), 249–260. https://doi.org/10.1017/S0261444819000041

Flowerdew, Lynne. 2022. Using corpora for writing instruction. In O’Keeffe, Anne & McCarthy, Michael J. (eds.), The Routledge handbook of corpus linguistics, 2nd edn., 443–455. London: Routledge.

https://doi.org/10.4324/9780367076399-31

Gilmore, Audrey & Carson, David & Perry, Chad. 2006. Academic publishing: Best practice for editors, guest editors, authors and reviewers. European Business Review 18(6). 468–478. https://doi.org/10.1108/09555340610711094

Giray, Louie. 2023. Prompt engineering with ChatGPT: A guide for academic writers. Annals of Biomedical Engineering 51, 2629–2633. https://doi.org/10.1007/s10439-023-03272-4

Gries, Stefan Th. 2008. Phraseology and linguistic theory: A brief survey. In Granger, Sylviane & Meunier, Fanny (eds.), Phraseology: An interdisciplinary perspective, 3–25. Amsterdam, Philadelphia: John Benjamins Publishing Company. https://doi.org/10.1075/z.139.06gri

Hanauer, David I. & Englander, Karen. 2011. Quantifying the burden of writing research articles in a second language: Data from Mexican scientists. Written Communication 28(4). 403–416. https://doi.org/10.1177/0741088311420056

Hanauer, David I. & Sheridan, Cheryl L. & Englander, Karen. 2019. Linguistic injustice in the writing of research articles in English as a second language: Data from Taiwanese and Mexican researchers. Written Communication 36(1), 136–154. https://doi.org/10.1177/0741088318804821

Hüsch, Marc & Horstmann, Nina & Breiter, Andreas. 2025. Künstliche Intelligenz im Studium – die Sicht von Studierenden im Wintersemester 2024/25. CHE Hochschuldaten. https://hochschuldaten.che.de/kuenstliche-intelligenz-im-studium-die-sicht-von-studierenden-im-wintersemester-2024-25/

(last accessed on 22/12/2025).

Hwang, Haerim & Chang, Xingyu & Sun, Jiaxin. 2025. Generative AI is useful for second language writing, but when, why, and for how long do learners use it? Journal of Second Language Writing 69.

https://doi.org/10.1016/j.jslw.2025.101230

Hyland, Ken. 2016a. Academic publishing and the myth of linguistic injustice. Journal of Second Language Writing 31, 58–69. https://doi.org/10.1016/j.jslw.2016.01.005

Hyland, Ken. 2016b. Language myths and publishing mysteries: A response to Politzer-Ahles et al. Journal of Second Language Writing 34, 9–11. https://doi.org/10.1016/j.jslw.2016.09.001

Imran, Muhammad & Almusharraf, Norah. 2023. Analyzing the role of ChatGPT as a writing assistant at higher education level: A systematic review of the literature. Contemporary Educational Technology 15(4). https://doi.org/10.30935/cedtech/13605

Kohnke, Lucas. Microlearning with GenAI: Enhancing second language education. Cambridge: Cambridge University Press. https://doi.org/10.1017/9781009642859

Koltovskaia, Svetlana & Rahmati, Payam & Saeli, Hooman. 2024. Graduate students’ use of ChatGPT for academic text revision: Behavioral, cognitive, and affective engagement. Journal of Second Language Writing 65. https://doi.org/10.1016/j.jslw.2024.101130

Leacock, Claudia & Chodorow, Martin & Gamon, Michael & Tetreault, Joel. 2014. Automated grammatical error detection for language learners. 2nd edn. San Rafael: Morgan & Claypool. https://doi.org/10.1007/978-3-031-02153-4

Lechien, Jerome R. & Gorton, Amy & Robertson, Jean & Vaira, Luigi A. 2023. Is ChatGPT‐4 accurate in proofread a manuscript in otolaryngology-head and neck surgery? Otolaryngology-Head and Neck Surgery 170(6), 1527–1530. https://doi.org/10.1002/ohn.526

Leitgeb, Thomas & Leitgeb, Michael. 2024. Empfehlungen für eine evidenzbasierte Nutzung von Künstlicher Intelligenz und Large Language Modells in Hochschulen: Ergebnisse eines systematischen Reviews. phpublico – Fachzeitschrift für Bildung und Erziehung, 1–34. https://doi.org/10.5281/ZENODO.13918915

Lennon, Paul. 1991. Error: Some problems of definition, identification, and distinction. Applied Linguistics 12(2), 180–196.

https://doi.org/10.1093/applin/12.2.180

Li, Mingyu & Wang, Fengqiang. 2026. EAL scholars’ experiences of writing for publication in English: A meta-ethnographic synthesis of qualitative evidence. English for Specific Purposes 81, 16–31.

https://doi.org/10.1016/j.esp.2025.09.001

Liu, Dilin. 2013a. Salience and construal in the use of synonymy: A study of two sets of near-synonymous nouns. Cognitive Linguistics 24(1), 67–113. https://doi.org/10.1515/cog-2013-0003

Liu, Dilin. 2013b. Using corpora to help teach difficult-to-distinguish English words. English Teaching 68(3). 27–50.

https://doi.org/10.15858/engtea.68.3.201309.27

Liu, Dilin & Lei, Lei. 2017. Using corpora for language learning and teaching. Alexandria, Virginia: tesol press.

Lo, Chung Kwan. 2023. What is the impact of ChatGPT on education? A rapid review of the literature. Education Sciences 13(4). https://doi.org/10.3390/educsci13040410

López-Navarro, Irene & Moreno, Ana I. & Quintanilla, Miguel Ángel & Rey-Rocha, Jesús. 2015. Why do I publish research articles in English instead of my own language? Differences in Spanish researchers’ motivations across scientific domains. Scientometrics 103, 939–976. https://doi.org/10.1007/s11192-015-1570-1

Mair, Christian. 2002. Empowering non-native speakers: The hidden surplus value of corpora in continental English departments. In Kettemann, Bernhard & Marko, Georg (eds.), Teaching and learning by doing corpus analysis: Proceedings of the fourth international conference on teaching and language corpora, Graz 19-24 July, 2000, 119–130. Leiden: De Gruyter Brill. https://doi.org/10.1163/9789004334236_011

McKinley, Jim & Rose, Heath. 2018. Conceptualizations of language errors, standards, norms and nativeness in English for research publication purposes: An analysis of journal submission guidelines. Journal of Second Language Writing 42, 1–11. https://doi.org/10.1016/j.jslw.2018.07.003

Ng, Davy Tsz Kit & Leung, Jac Ka Leung & Chu, Samuel Kai Wah & Qiao, Maggie Shen. 2021. Conceptualizing AI literacy: An exploratory review. Computers and Education: Artificial Intelligence 2.

https://doi.org/10.1016/j.caeai.2021.100041

Ng, Hwee Tou & Wu, Siew Mei & Briscoe, Ted & Hadiwinoto, Christian & Susanto, Raymond Hendy & Bryant, Christopher. 2014. The CoNLL-2014 shared task on grammatical error correction. In Ng, Hwee Tou & Wu, Siew Mei & Briscoe, Ted & Hadiwinoto, Christian & Susanto, Raymond Hendy & Bryant, Christopher (eds.), Proceedings of the eighteenth conference on computational natural language learning: Shared task, 1–14. Baltimore, Maryland: Association for Computational Linguistics. https://doi.org/10.3115/v1/W14-1701

OECD. 2025. Empowering learners for the age of AI: An AI literacy framework for primary and secondary education (Review draft). OECD. https://ailiteracyframework.org/

Ouyang, Shuyin & Zhang, Jie M. & Harman, Mark & Wang, Meng. 2025. An empirical study of the non-determinism of ChatGPT in code generation. ACM Transactions on Software Engineering and Methodology 34(2), 1–28. https://doi.org/10.1145/3697010

Parkes, Geoff. 2003. The mistakes clinic for German-speaking learners of English: Error correction exercises and detailed error analysis for German-speaking students and teachers of English (Reprinted with corr.). Southampton: Englang Books.

Pfau, Adam & Polio, Charlene & Xu, Yiran. 2023. Exploring the potential of ChatGPT in assessing L2 writing accuracy for research purposes. Research Methods in Applied Linguistics 2(3).

https://doi.org/10.1016/j.rmal.2023.100083

Politzer-Ahles, Stephen & Girolamo, Teresa & Ghali, Samantha. 2020. Preliminary evidence of linguistic bias in academic reviewing. Journal of English for Academic Purposes 47. https://doi.org/10.1016/j.jeap.2020.100895

Quinn, Cynthia. 2015. Training L2 writers to reference corpora as a self-correction tool. ELT Journal 69(2), 165-177. https://doi.org/10.1093/elt/ccu062

Quirk, Randolph & Greenbaum, Sidney & Leech, Geoffrey & Svartvik, Jan. 1985. A comprehensive grammar of the English language. London: Longman.

Ramírez-Castañeda, Valeria. 2020. Disadvantages in preparing and publishing scientific papers caused by the dominance of the English language in science: The case of Colombian researchers in biological sciences. PLoS ONE 15(9). https://doi.org/10.1371/journal.pone.0238372

Rankin, Tom & Schiftner, Barbara. 2011. Marginal prepositions in learner English: Applying local corpus data. International Journal of Corpus Linguistics 16(3), 412–434. https://doi.org/10.1075/ijcl.16.3.07ran

Rich, Elaine & Knight, Kevin. 1991. Artificial intelligence. 2nd edn. New York: McGraw-Hill.

Rohdenburg, Günter. 2003. Cognitive complexity and horror aequi as factors determining the use of interrogative clause linkers in English. In Rohdenburg, Günter & Mondorf, Britta (eds.), Determinants of grammatical variation in English, 205–250. Berlin, New York: Mouton de Gruyter. https://doi.org/10.1515/9783110900019.205

Schlüter, Julia & Deckert, Katharina. 2025. Artificial Intelligence vs. Corpus Literacy: Ansätze zur Vermittlung reflektierter Schreibkompetenz in der Wissenschaftssprache Englisch. In Mrohs, Lorenz & Franz, Julia & Herrmann, Dominik & Lindner, Konstantin & Staake, Thorsten (eds.), Digitales Lehren und Lernen an der Hochschule: Strategien – Bedingungen – Umsetzung, 111–119. Bielefeld: transcript Verlag. https://doi.org/10.1515/9783839471203-011

Sheldon, Elena. 2020. ‘We cannot abandon the two worlds, we have to be in both’: Chilean scholars’ views on publishing in English and Spanish. Journal of English for Research Publication Purposes 1(2), 120–142. https://doi.org/10.1075/jerpp.19016.she

Son, Jeong-Bae & Philpott, Andrew. 2026. AI-Powered language teaching. Cambridge: Cambridge University Press.

https://doi.org/10.1017/9781009650809

Staples, Shelley & Egbert, Jesse & Biber, Douglas & Conrad, Susan. 2015. Register variation: A corpus approach. In Tannen, Deborah & Hamilton, Heidi E. & Schiffrin, Deborah (eds.), The Handbook of Discourse Analysis, 2nd edn., 505–525. West Sussex: John Wiley & Sons, Inc. https://doi.org/10.1002/9781118584194.ch24

Strauss, Pat. 2019. Shakespeare and the English poets: The influence of native speaking English reviewers on the acceptance of journal articles. Publications 7(1). https://doi.org/10.3390/publications7010020

Tan, Xiao. 2025. Academic socialization with generative AI: A longitudinal case study of an L2 graduate student’s academic literacies development. Journal of Second Language Writing 70. https://doi.org/10.1016/j.jslw.2025.101263

Timmis, Ivor. 2015. Corpora in perspective. In Corpus linguistics for ELT: research and practice, 183–195. London, New York: Routledge, Taylor & Francis Group. https://doi.org/10.4324/9781315715537

Turner, Joan. 2004. Language as academic purpose. Journal of English for Academic Purposes 3(2), 95–109.

https://doi.org/10.1016/S1475-1585(03)00054-7

Uzuner, Sedef. 2008. Multilingual scholars’ participation in core/global academic communities: A literature review. Journal of English for Academic Purposes 7(4), 250–263. https://doi.org/10.1016/j.jeap.2008.10.007

Warschauer, Mark & Tseng, Waverly & Yim, Soobin & Webster, Thomas & Jacob, Sharin & Du, Qian & Tate, Tamara. 2023. The affordances and contradictions of AI-generated text for writers of English as a second or foreign language. Journal of Second Language Writing 62. https://doi.org/10.1016/j.jslw.2023.101071

Wu, Haoran & Wang, Wenxuan & Wan, Yuxuan & Jiao, Wenxiang & Lyu, Michael. 2023. ChatGPT or Grammarly? Evaluating ChatGPT on grammatical error correction benchmark. arXiv. https://doi.org/10.48550/arXiv.2303.13648

Xu, Jian. 2025. Harnessing AI in academic writing: The complex interplay of AI literacy and self-directed learning among university L2 learners. System 135. https://doi.org/10.1016/j.system.2025.103855

Xu, Yiran & Polio, Charlene & Pfau, Adam. 2024. Optimizing AI for assessing L2 writing accuracy: An exploration of temperatures and prompts. In Chapelle, Carol A. & Beckett, Gulbahar H. & Ranalli, Jim (eds.), Exploring Artificial Intelligence in Applied Linguistics, 151–174. Iowa: Iowa State University Digital Press. https://doi.org/10.31274/isudp.2024.154.10

Details