---
title: "GhostWriter: Hidden AI-Generated Texts over — Schaaf 2026"
description: "Detectors of AI-generated text (AIGT) are usually trained and tested on English material from older models like GPT-2 or GPT-3.5, and they mostly label…"
authors: ["Manuel Schaaf", "Kevin Bönisch", "Alexander Mehler"]
year: 2026
venue: "Proceedings of the Fifteenth Language Resources and Evaluation Conference"
source: "https://aclanthology.org/2026.lrec-1.823/"
doi: "10.63317/57fd7juh5zek"
licence: "CC BY-NC 4.0 (ELRA, LREC proceedings)"
licence_url: "https://creativecommons.org/licenses/by-nc/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/papers/schaaf-2026-ghostwriter-hidden-ai-generated-texts/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/schaaf-2026-ghostwriter-hidden-ai-generated-texts/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2026](https://md.research.elamur.ai/free/papers/2026/page/3/) / GhostWriter: Hidden AI-Generated Texts over Multiple Languages, Domains and Generators

# GhostWriter: Hidden AI-Generated Texts over Multiple Languages, Domains and Generators

**Authors:** Manuel Schaaf, Kevin Bönisch, [Alexander Mehler](https://md.research.elamur.ai/free/authors/alexander-mehler/) · **Year:** 2026 · **Venue:** Proceedings of the Fifteenth Language Resources and Evaluation Conference · **Licence:** [CC BY-NC 4.0 (ELRA, LREC proceedings)](https://creativecommons.org/licenses/by-nc/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.lrec-1.823/) · [PDF](https://aclanthology.org/2026.lrec-1.823.pdf) · [DOI 10.63317/57fd7juh5zek](https://doi.org/10.63317/57fd7juh5zek) · [OpenAlex](https://openalex.org/W7160188018)

**Citations:** 0 citations (openalex-snapshot · 2026-10-14)

## Summary
Detectors of AI-generated text (AIGT) are usually trained and tested on English material from older models like GPT-2 or GPT-3.5, and they mostly label whole documents. That leaves gaps for German and for realistic ghostwriting, where someone hides machine-written passages inside human text. To fill these gaps, the authors built GhostWriter, a German–English benchmark spanning several domains and generators. Its human side draws on news, arXiv papers, blogs, parliamentary speeches, ECHR court cases, student essays and Project Gutenberg literature. These texts serve as seeds for synthetic counterparts written by current LLMs under domain-specific ghostwriting prompts. The resource includes both fully generated documents and "fusion" texts, in which AI chunks are mixed into human writing. Likelihood-based and supervised baselines show that zero-shot detectors such as Binoculars perform well on whole documents. However, blogs remain difficult, and fusion texts substantially lower the scores. GhostWriter therefore provides a fresh, German-inclusive testbed for detecting AIGT at the chunk level.

## Key points
- **Human sources:** All human texts predate the end of 2020, so they should be free of LLM output. They comprise:
  - 18,773 CNN-DailyMail articles
  - 8,448 arXiv papers
  - 20,299 blogger.com posts
  - 18,343 German Bundestag speeches (Bundestag-Mine) and 13,896 House of Commons speeches
  - 9,148 ECHR cases
  - 42,311 student essays
  - 7,224 Gutenberg works
- **Generators:** The evaluation covers deepseek-r1 (1.5b and 32b), gemma2:9b, gpt-4-turbo, gpt-4o-mini, nemotron, o3-mini and phi3:3.8b.
- **Baselines without fusion texts:** Binoculars scores best overall (F1 0.892, AUC 0.937, FPR 0.063), followed by Fast-DetectGPT (F1 0.859) and DetectLLM LLR (F1 0.780). The supervised RADAR (F1 0.483) and E5-LoRA (F1 0.604) trail behind.
- **Effect of fusion texts:** Including them reduces AUC for the supervised models, from 0.698 to 0.634 for RADAR and from 0.821 to 0.670 for E5-LoRA. Across detectors, blogs are the hardest domain, with F1 around 0.6–0.66.
- **Availability:** The dataset is published on HuggingFace as `TheItCrOw/GhostWriter`.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Linguistics & languages](https://md.research.elamur.ai/free/shelves/linguistics/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{schaaf2026ghostwriter,
  title = {{GhostWriter: Hidden AI-Generated Texts over Multiple Languages, Domains and Generators}},
  author = {Schaaf, Manuel and Bönisch, Kevin and Mehler, Alexander},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/57fd7juh5zek},
  url = {https://doi.org/10.63317/57fd7juh5zek}
}
```

- [← previous GHAD NLP at AdabEval2026: Transformer-Based Approach for Arabic Politeness and Pragmatic Category Classification](https://md.research.elamur.ai/free/papers/alfattni-2026-ghad-nlp-adabeval2026-transformer-based/)
- [next → GPT-NL Public Corpus: A Permissively Licensed, Dutch-First Dataset for LLM Pre-training](https://md.research.elamur.ai/free/papers/oort-2026-gpt-nl-public-corpus-permissively/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/papers/2026/page/3/)

## References

64 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Marah Abdin, Jyoti Aneja, Hany Awadalla, Ahmed Awadallah, Ammar Ahmad Awan, Nguyen Bach, Amit Bahree, Arash Bakhtiari, Jianmin Bao, et al. 2024. Phi-3 technical report: A highly capable language model locally on your phone. [↗](https://doi.org/10.48550/arxiv.2404.14219) [our card](https://md.research.elamur.ai/free/papers/abdin-2024-phi-3-technical-report-highly/)
2. Ebtesam Almazrouei, Hamza Alobeidli, Abdulaziz Alshamsi, Alessandro Cappelli, Ruxandra Cojocaru, Mérouane Debbah, Étienne Goffinet, Daniel Hesslow, Julien Launay, Quentin Malartic, Daniele Mazzotta, Badreddine Noune, Baptiste Pannier, and Guilherme Penedo. 2023. The Falcon Series of Open Language Models. CoRR, abs/2311.16867. [↗](https://arxiv.org/abs/2311.16867) [our card](https://md.research.elamur.ai/free/papers/almazrouei-2023-falcon-series-open-language-models/)
3. Guangsheng Bao, Yanbin Zhao, Zhiyang Teng, Linyi Yang, and Yue Zhang. 2024. Fast-detectgpt: Efficient zero-shot detection of machine-generated text via conditional probability curvature. [↗](https://doi.org/10.48550/arxiv.2310.05130) [our card](https://md.research.elamur.ai/free/papers/bao-2023-fast-detectgpt-efficient-zero-shot/)
4. Théophile Bisi, Anthony Risser, Philippe Clavert, Henri Migaud, and Julien Dartus. 2023. What is the rate of text generated by artificial intelligence over a year of publication in orthopedics & traumatology: Surgery & research? analysis of 425 articles before versus after the launch of chatgpt in november 2022. Orthopaedics & Traumatology: Surgery & Research, 109(8):103694. [↗](https://doi.org/10.1016/j.otsr.2023.103694)
5. Jack Blumenau. 2021. Measuring political debate: Responsiveness, influence, and rhetoric in parliamentary texts. Dataset. Sponsored by the Economic and Social Research Council, Grant reference: ES/N016297/1. [find](https://scholar.google.com/scholar?q=Jack+Blumenau%2E+2021%2E+Measuring+political+debate%3A+Responsiveness%2C+influence%2C+and+rhetoric+in+parliamentary+texts%2E+Dataset%2E+Sponsored+by+the+Economic+and+Social+Research+Council%2C+Grant+reference%3A+ES%2FN01)
6. Kevin Bönisch, Giuseppe Abrami, Sabine Wehnert, and Alexander Mehler. 2023. Bundestags-Mine: Natural language processing for extracting key information from government documents. In Legal Knowledge and Information Systems. IOS Press. [find](https://scholar.google.com/scholar?q=Kevin+B%C3%B6nisch%2C+Giuseppe+Abrami%2C+Sabine+Wehnert%2C+and+Alexander+Mehler%2E+2023%2E+Bundestags%2DMine%3A+Natural+language+processing+for+extracting+key+information+from+government+documents%2E+In+Legal+Knowledge+an)
7. Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language models are few-shot learners. [↗](https://doi.org/10.48550/arxiv.2005.14165)
8. Ilias Chalkidis, Manos Fergadiotis, Dimitrios Tsarapatsanis, Nikolaos Aletras, Ion Androutsopoulos, and Prodromos Malakasiotis. 2021. Paragraph-level rationale extraction through regularization: A case study on European court of human rights cases. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 226–241, Online. Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.2103.13084) [our card](https://md.research.elamur.ai/free/papers/chalkidis-2021-paragraph-level-rationale-extraction-through/)
9. Tianqi Chen and Carlos Guestrin. 2016. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’16, page 785–794. ACM. [↗](https://doi.org/10.48550/arxiv.1603.02754)
10. Wei-Lin Chiang, Zhuohan Li, Ziqing Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E Gonzalez, et al. 2023. Vicuna: An Open-Source Chatbot impressing GPT-4 with 90%* ChatGPT Quality. Accessed 16. [find](https://scholar.google.com/scholar?q=Wei%2DLin+Chiang%2C+Zhuohan+Li%2C+Ziqing+Lin%2C+Ying+Sheng%2C+Zhanghao+Wu%2C+Hao+Zhang%2C+Lianmin+Zheng%2C+Siyuan+Zhuang%2C+Yonghao+Zhuang%2C+Joseph+E+Gonzalez%2C+et+al%2E+2023%2E+Vicuna%3A+An+Open%2DSource+Chatbot+impressing+GPT%2D)
11. Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. 2020. Unsupervised cross-lingual representation learning at scale. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8440–8451, Online. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/2020.acl-main.747)
12. S.A. Crossley, Y. Tian, P. Baffour, A. Franklin, M. Benner, and U. Boser. 2024. A large-scale corpus for assessing written argumentation: Persuade 2.0. Assessing Writing, 61:100865. [↗](https://doi.org/10.1016/j.asw.2024.100865)
13. DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. [find](https://scholar.google.com/scholar?q=DeepSeek%2DAI%2C+Daya+Guo%2C+Dejian+Yang%2C+Haowei+Zhang%2C+Junxiao+Song%2C+Ruoyu+Zhang%2C+Runxin+Xu%2C+Qihao+Zhu%2C+Shirong+Ma%2C+Peiyi+Wang%2C+et+al%2E+2025%2E+Deepseek%2Dr1%3A+Incentivizing+reasoning+capability+in+llms+via+rein) [our card](https://md.research.elamur.ai/free/papers/deepseek-2025-ai-deepseek-r1-incentivizing-reasoning-capability/)
14. Faisal R. Elali and Leena N. Rachid. 2023. Ai-generated research paper fabrication and plagiarism in the scientific community. Patterns, 4(3):100706. [↗](https://doi.org/10.1016/j.patter.2023.100706)
15. Carlos Gómez-Rodríguez and Paul Williams. 2023. A confederacy of models: a comprehensive evaluation of LLMs on creative writing. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 14504–14528, Singapore. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Carlos+G%C3%B3mez%2DRodr%C3%ADguez+and+Paul+Williams%2E+2023%2E+A+confederacy+of+models%3A+a+comprehensive+evaluation+of+LLMs+on+creative+writing%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+EMNLP+202)
16. Project Gutenberg. n.d. Project gutenberg. Retrieved February 21, 2016, from [https://www.gutenberg.org](https://www.gutenberg.org). [↗](https://www.gutenberg.org)
17. Hans W. A. Hanley and Zakir Durumeric. 2023. Machine-made media: Monitoring the mobilization of machine-generated articles on misinformation and mainstream news websites. In International Conference on Web and Social Media. [find](https://scholar.google.com/scholar?q=Hans+W%2E+A%2E+Hanley+and+Zakir+Durumeric%2E+2023%2E+Machine%2Dmade+media%3A+Monitoring+the+mobilization+of+machine%2Dgenerated+articles+on+misinformation+and+mainstream+news+websites%2E+In+International+Conference+o)
18. Abhimanyu Hans, Avi Schwarzschild, Valeriia Cherepanova, Hamid Kazemi, Aniruddha Saha, Micah Goldblum, Jonas Geiping, and Tom Goldstein. 2024. Spotting llms with binoculars: zero-shot detection of machine-generated text. In Proceedings of the 41st International Conference on Machine Learning, ICML’24. JMLR.org. [↗](https://doi.org/10.48550/arxiv.2401.12070)
19. Karl Moritz Hermann, Tomáš Kočiský, Edward Grefenstette, Lasse Espeholt, Will Kay, Mustafa Suleyman, and Phil Blunsom. 2015. Teaching machines to read and comprehend. [↗](https://doi.org/10.48550/arxiv.1506.03340) [our card](https://md.research.elamur.ai/free/papers/hermann-2015-teaching-machines-read-comprehend/)
20. Xiaomeng Hu, Pin-Yu Chen, and Tsung-Yi Ho. 2023. Radar: Robust ai-text detection via adversarial learning. [find](https://scholar.google.com/scholar?q=Xiaomeng+Hu%2C+Pin%2DYu+Chen%2C+and+Tsung%2DYi+Ho%2E+2023%2E+Radar%3A+Robust+ai%2Dtext+detection+via+adversarial+learning%2E)
21. INTERPOL. 2023. ChatGPT: Impacts on Law Enforcement. [find](https://scholar.google.com/scholar?q=INTERPOL%2E+2023%2E+ChatGPT%3A+Impacts+on+Law+Enforcement%2E)
22. Juyong Jiang, Fan Wang, Jiasi Shen, Sungju Kim, and Sunghun Kim. 2024. A survey on large language models for code generation. Jina AI. PromptPerfect. [↗](https://doi.org/10.1145/3747588) [our card](https://md.research.elamur.ai/free/papers/jiang-2024-survey-large-language-models-code/)
23. Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu. 2017. Lightgbm: A highly efficient gradient boosting decision tree. In Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc. [find](https://scholar.google.com/scholar?q=Guolin+Ke%2C+Qi+Meng%2C+Thomas+Finley%2C+Taifeng+Wang%2C+Wei+Chen%2C+Weidong+Ma%2C+Qiwei+Ye%2C+and+Tie%2DYan+Liu%2E+2017%2E+Lightgbm%3A+A+highly+efficient+gradient+boosting+decision+tree%2E+In+Advances+in+Neural+Information+)
24. Mohamed Khalifa and Mona Albadawy. 2024. Using artificial intelligence in academic writing and research: An essential productivity tool. Computer Methods and Programs in Biomedicine Update, 5:100145. [↗](https://doi.org/10.1016/j.cmpbup.2024.100145)
25. Jaeho Kim, Yunseok Lee, and Seulki Lee. 2025. Position: The AI conference peer review crisis demands author feedback and reviewer rewards. In Forty-second International Conference on Machine Learning Position Paper Track. [↗](https://doi.org/10.48550/arxiv.2505.04966)
26. Jules King, Perpetual Baffour, Scott Crossley, Ryan Holbrook, and Maggie Demkin. 2023. Llm - detect ai generated text. [https://kaggle.com/competitions/llm-detect-ai-generated-text](https://kaggle.com/competitions/llm-detect-ai-generated-text). Kaggle. [↗](https://kaggle.com/competitions/llm-detect-ai-generated-text)
27. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pre-training approach. [find](https://scholar.google.com/scholar?q=Yinhan+Liu%2C+Myle+Ott%2C+Naman+Goyal%2C+Jingfei+Du%2C+Mandar+Joshi%2C+Danqi+Chen%2C+Omer+Levy%2C+Mike+Lewis%2C+Luke+Zettlemoyer%2C+and+Veselin+Stoyanov%2E+2019%2E+Roberta%3A+A+robustly+optimized+bert+pre%2Dtraining+approach%2E)
28. Chris Lu, Cong Lu, Robert Tjarko Lange, Jakob Foerster, Jeff Clune, and David Ha. 2024. The ai scientist: Towards fully automated open-ended scientific discovery. [↗](https://doi.org/10.48550/arxiv.2408.06292) [our card](https://md.research.elamur.ai/free/papers/lu-2024-ai-scientist-fully-automated/)
29. Nestor Maslej, Loredana Fattorini, Raymond Perrault, Vanessa Parli, Anka Reuel, Erik Brynjolfsson, John Etchemendy, Katrina Ligett, Terah Lyons, James Manyika, Juan Carlos Niebles, Yoav Shoham, Russell Wald, and Jack Clark. 2024. Artificial intelligence index report 2024. [↗](https://doi.org/10.48550/arxiv.2405.19522)
30. Soichiro Murakami, Sho Hoshino, and Peinan Zhang. 2023. Natural language generation for advertising: A survey. [↗](https://doi.org/10.48550/arxiv.2306.12719)
31. Meriame Naddaf. 2025. Ai linked to explosion of low-quality biomedical research papers. Nature, 641(8065):1080–1081. [↗](https://doi.org/10.1038/d41586-025-01592-0)
32. Nvidia, Bo Adler, Niket Agarwal, Ashwath Aithal, Dong H. Anh, Pallab Bhattacharya, Annika Brundyn, Jared Casper, et al. 2024. Nemotron-4 340b technical report. [↗](https://doi.org/10.48550/arxiv.2406.11704)
33. OpenAI. 2024. Gpt-4o mini: advancing cost-efficient intelligence. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2024%2E+Gpt%2D4o+mini%3A+advancing+cost%2Defficient+intelligence%2E)
34. OpenAI. 2025. Openai o3-mini. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2025%2E+Openai+o3%2Dmini%2E)
35. OpenAI, Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, et al. 2024. Gpt-4 technical report. [↗](https://doi.org/10.4230/lipics.cosit.2024.11) [our card](https://md.research.elamur.ai/free/papers/openai-2023-gpt-4-technical-report/)
36. Shushanta Pudasaini, Luis Miralles-Pechuán, David Lillis, and Marisa Llorens Salvador. 2024. Survey on plagiarism detection in large language models: The impact of chatgpt and gemini on academic integrity. [↗](https://doi.org/10.48550/arxiv.2407.13105)
37. Jonathan Schler, Moshe Koppel, Shlomo Engelson Argamon, and James W. Pennebaker. 2006. Effects of age and gender on blogging. In AAAI Spring Symposium: Computational Approaches to Analyzing Weblogs. [find](https://scholar.google.com/scholar?q=Jonathan+Schler%2C+Moshe+Koppel%2C+Shlomo+Engelson+Argamon%2C+and+James+W%2E+Pennebaker%2E+2006%2E+Effects+of+age+and+gender+on+blogging%2E+In+AAAI+Spring+Symposium%3A+Computational+Approaches+to+Analyzing+Weblogs%2E)
38. Yang Shen and Xiuwu Zhang. 2024. The impact of artificial intelligence on employment: the role of virtual agglomeration. Palgrave Communications, 11(1):1–14. [↗](https://doi.org/10.1057/s41599-024-02647-9)
39. Ilia Shumailov, Zakhar Shumaylov, Yiren Zhao, Nicolas Papernot, Ross Anderson, and Yarin Gal. 2024. Ai models collapse when trained on recursively generated data. Nature, 631(8022):755– 759. [↗](https://doi.org/10.1038/s41586-024-07566-y)
40. Md Kamrul Siam, Huanying Gu, and Jerry Q. Cheng. 2024. Programming with ai: Evaluating chatgpt, gemini, alphacode, and github copilot for programmers. [find](https://scholar.google.com/scholar?q=Md+Kamrul+Siam%2C+Huanying+Gu%2C+and+Jerry+Q%2E+Cheng%2E+2024%2E+Programming+with+ai%3A+Evaluating+chatgpt%2C+gemini%2C+alphacode%2C+and+github+copilot+for+programmers%2E)
41. Jinyan Su, Terry Zhuo, Di Wang, and Preslav Nakov. 2023. DetectLLM: Leveraging log rank information for zero-shot detection of machine-generated text. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 12395–12412, Singapore. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Jinyan+Su%2C+Terry+Zhuo%2C+Di+Wang%2C+and+Preslav+Nakov%2E+2023%2E+DetectLLM%3A+Leveraging+log+rank+information+for+zero%2Dshot+detection+of+machine%2Dgenerated+text%2E+In+Findings+of+the+Association+for+Computational+)
42. Tulsi Suchak, Anietie E. Aliu, Charlie Harrison, Reyer Zwiggelaar, Nophar Geifman, and Matt Spick. 2025. Explosion of formulaic research articles, including inappropriate study designs and false discoveries, based on the nhanes us national health database. PLOS Biology, 23(5):e3003152. Published 8 May 2025. [↗](https://doi.org/10.1371/journal.pbio.3003152)
43. Gemini Team, Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, et al. 2024a. Gemini: A family of highly capable multimodal models. [↗](https://doi.org/10.48550/arxiv.2312.11805) [our card](https://md.research.elamur.ai/free/papers/gemini-2023-team-gemini-family-highly-capable-multimodal/)
44. Gemma Team, Morgane Riviere, Shreya Pathak, Pier Giuseppe Sessa, Cassidy Hardin, Surya Bhupatiraju, Léonard Hussenot, et al. 2024b. Gemma 2: Improving open language models at a practical size. [↗](https://doi.org/10.48550/arxiv.2408.00118)
45. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. Llama: Open and efficient foundation language models. [↗](https://doi.org/10.48550/arxiv.2302.13971)
46. Ashish Vaswani, Noam M. Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Ashish+Vaswani%2C+Noam+M%2E+Shazeer%2C+Niki+Parmar%2C+Jakob+Uszkoreit%2C+Llion+Jones%2C+Aidan+N%2E+Gomez%2C+Lukasz+Kaiser%2C+and+Illia+Polosukhin%2E+2017%2E+Attention+is+all+you+need%2E+In+Neural+Information+Processing+Syste)
47. Veniamin Veselovsky, Manoel Horta Ribeiro, and Robert West. 2023. Artificial artificial artificial intelligence: Crowd workers widely use large language models for text production tasks. [↗](https://doi.org/10.48550/arxiv.2306.07899)
48. Kuang-Hsien Wang and Wen-Cheng Lu. 2025. Ai-induced job impact: Complementary or substitution? empirical insights and sustainable technology considerations. Sustainable Technology and Entrepreneurship, 4(1):100085. [↗](https://doi.org/10.1016/j.stae.2024.100085)
49. Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, and Furu Wei. 2022. Text embeddings by weakly-supervised contrastive pre-training. 8. [↗](https://doi.org/10.48550/arxiv.2212.03533) [our card](https://md.research.elamur.ai/free/papers/wang-2022-text-embeddings-weakly-supervised-contrastive/)
50. Language Resource References Yutian Chen, Hao Kang, Vivian Zhai, Liangze Li, Rita Singh, and Bhiksha Raj. 2023. Token prediction as implicit classification to identify LLM-generated text. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 13112–13120, Singapore. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Language+Resource+References+Yutian+Chen%2C+Hao+Kang%2C+Vivian+Zhai%2C+Liangze+Li%2C+Rita+Singh%2C+and+Bhiksha+Raj%2E+2023%2E+Token+prediction+as+implicit+classification+to+identify+LLM%2Dgenerated+text%2E+In+Proceedin)
51. Liam Dugan, Alyssa Hwang, Filip Trhlík, Andrew Zhu, Josh Magnus Ludan, Hainiu Xu, Daphne Ippolito, and Chris Callison-Burch. 2024. RAID: A shared benchmark for robust evaluation of machine-generated text detectors. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12463–12492, Bangkok, Thailand. Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.2405.07940)
52. Biyang Guo, Xin Zhang, Ziyuan Wang, Minqi Jiang, Jinran Nie, Yuxuan Ding, Jianwei Yue, and Yupeng Wu. 2023. How close is chatgpt to human experts? comparison corpus, evaluation, and detection. [↗](https://doi.org/10.48550/arxiv.2301.07597) [our card](https://md.research.elamur.ai/free/papers/guo-2023-close-chatgpt-human-experts-comparison/)
53. Oana Ignat, Xiaomeng Xu, and Rada Mihalcea. 2025. MAiDE-up: Multilingual deception detection of AI-generated hotel reviews. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 1636–1653, Albuquerque, New Mexico. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Oana+Ignat%2C+Xiaomeng+Xu%2C+and+Rada+Mihalcea%2E+2025%2E+MAiDE%2Dup%3A+Multilingual+deception+detection+of+AI%2Dgenerated+hotel+reviews%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+NAACL+2025%2C+pa)
54. Linyang Li, Pengyu Wang, Ke Ren, Tianxiang Sun, and Xipeng Qiu. 2023. Origin tracing and detecting of llms. [↗](https://doi.org/10.48550/arxiv.2304.14072)
55. Yafu Li, Qintong Li, Leyang Cui, Wei Bi, Zhilin Wang, Longyue Wang, Linyi Yang, Shuming Shi, and Yue Zhang. 2024. MAGE: Machine-generated text detection in the wild. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 36–53, Bangkok, Thailand. Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.2305.13242)
56. Yikang Liu, Ziyin Zhang, Wanyang Zhang, Shisen Yue, Xiaojing Zhao, Xinyuan Cheng, Yiwen Zhang, and Hai Hu. 2023. Argugpt: evaluating, understanding and identifying argumentative essays generated by gpt models. [↗](https://doi.org/10.48550/arxiv.2304.07666)
57. Dominik Macko, Jakub Kopál, Robert Moro, and Ivan Srba. 2025. MultiSocial: Multilingual benchmark of machine-generated text detection of social-media texts. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 727–752, Vienna, Austria. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Dominik+Macko%2C+Jakub+Kop%C3%A1l%2C+Robert+Moro%2C+and+Ivan+Srba%2E+2025%2E+MultiSocial%3A+Multilingual+benchmark+of+machine%2Dgenerated+text+detection+of+social%2Dmedia+texts%2E+In+Proceedings+of+the+63rd+Annual+Meeting+o)
58. Dominik Macko, Robert Moro, Adaku Uchendu, Jason Lucas, Michiharu Yamashita, Matúš Pikuliak, Ivan Srba, Thai Le, Dongwon Lee, Jakub Simko, and Maria Bielikova. 2023. MULTITuDE: Large-scale multilingual machine-generated text detection benchmark. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 9960–9987, Singapore. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Dominik+Macko%2C+Robert+Moro%2C+Adaku+Uchendu%2C+Jason+Lucas%2C+Michiharu+Yamashita%2C+Mat%C3%BA%C5%A1+Pikuliak%2C+Ivan+Srba%2C+Thai+Le%2C+Dongwon+Lee%2C+Jakub+Simko%2C+and+Maria+Bielikova%2E+2023%2E+MULTITuDE%3A+Large%2Dscale+multilingua)
59. Jiameng Pu, Zain Sarwar, Sifat Muhammad Abdullah, Abdullah Rehman, Yoonjin Kim, Parantapa Bhattacharya, Mobin Javed, and Bimal Viswanath. 2023. Deepfake text detection: Limitations and opportunities. In 44th IEEE Symposium on Security and Privacy, SP 2023, San Francisco, CA, USA, May 21-25, 2023, pages 1613–1630. IEEE. [find](https://scholar.google.com/scholar?q=Jiameng+Pu%2C+Zain+Sarwar%2C+Sifat+Muhammad+Abdullah%2C+Abdullah+Rehman%2C+Yoonjin+Kim%2C+Parantapa+Bhattacharya%2C+Mobin+Javed%2C+and+Bimal+Viswanath%2E+2023%2E+Deepfake+text+detection%3A+Limitations+and+opportunities%2E+)
60. Zhenpeng Su, Xing Wu, Wei Zhou, Guangyuan Ma, and Songlin Hu. 2024. Hc3 plus: A semantic-invariant human chatgpt comparison corpus. [↗](https://doi.org/10.48550/arxiv.2309.02731)
61. Vivek Verma, Eve Fleisig, Nicholas Tomlin, and Dan Klein. 2024. Ghostbuster: Detecting text ghostwritten by large language models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 1702– 1717, Mexico City, Mexico. Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.2305.15047)
62. Pengyu Wang, Linyang Li, Ke Ren, Botian Jiang, Dong Zhang, and Xipeng Qiu. 2023. SeqXGPT: Sentence-level AI-generated text detection. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 1144–1156, Singapore. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Pengyu+Wang%2C+Linyang+Li%2C+Ke+Ren%2C+Botian+Jiang%2C+Dong+Zhang%2C+and+Xipeng+Qiu%2E+2023%2E+SeqXGPT%3A+Sentence%2Dlevel+AI%2Dgenerated+text+detection%2E+In+Proceedings+of+the+2023+Conference+on+Empirical+Methods+in+Natu)
63. Yuxia Wang, Jonibek Mansurov, Petar Ivanov, Jinyan Su, Artem Shelmanov, Akim Tsvigun, Chenxi Whitehouse, Osama Mohammed Afzal, Tarek Mahmoud, Toru Sasaki, Thomas Arnold, Alham Fikri Aji, Nizar Habash, Iryna Gurevych, and Preslav Nakov. 2024. M4: Multi-generator, multi-domain, and multi-lingual black-box machine-generated text detection. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1369– 1407, St. Julian’s, Malta. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Yuxia+Wang%2C+Jonibek+Mansurov%2C+Petar+Ivanov%2C+Jinyan+Su%2C+Artem+Shelmanov%2C+Akim+Tsvigun%2C+Chenxi+Whitehouse%2C+Osama+Mohammed+Afzal%2C+Tarek+Mahmoud%2C+Toru+Sasaki%2C+Thomas+Arnold%2C+Alham+Fikri+Aji%2C+Nizar+Habash%2C)
64. Peipeng Yu, Jiahan Chen, Xuan Feng, and Zhihua Xia. 2025. CHEAT: A Large-Scale Dataset for Detecting CHatGPT-writtEn AbsTracts. IEEE Transactions Big Data, 11(3):898–906. [↗](https://doi.org/10.1109/tbdata.2025.3536929)