---
title: "Breaking the Generator Barrier — paper by Pu et al. (2026)"
description: "They propose a three-stage framework that separates authenticity cues (human vs. AI) from generator-specific traits. 42 references."
authors: ["Xiao Pu", "Zepeng Cheng", "Lin Yuan", "Yu Wu", "Xiuli Bi"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.120/"
doi: "10.18653/v1/2026.acl-long.120"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/pu-2026-breaking-generator-barrier-disentangled-representation/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/pu-2026-breaking-generator-barrier-disentangled-representation/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/24/) / Breaking the Generator Barrier: Disentangled Representation for Generalizable AI-Text Detection

# Breaking the Generator Barrier: Disentangled Representation for Generalizable AI-Text Detection

**Authors:** [Xiao Pu](https://md.research.elamur.ai/free/en/authors/xiao-pu/), Zepeng Cheng, Lin Yuan, [Yu Wu](https://md.research.elamur.ai/free/en/authors/yu-wu/) and Xiuli Bi · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.acl-long.120/) · [PDF](https://aclanthology.org/2026.acl-long.120.pdf) · [DOI 10.18653/v1/2026.acl-long.120](https://doi.org/10.18653/v1/2026.acl-long.120) · [OpenAlex](https://openalex.org/W7166880041)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary

AI-text detectors often learn quirks of the specific LLMs they were trained on, so they fail on newer, unseen generators. Pu et al. treat this generator shift as its own problem, distinct from ordinary domain shift. They propose a three-stage framework that separates authenticity cues (human vs. AI) from generator-specific traits.

1. **Dual-bottleneck encoding.** Two variational branches built on BERT's [CLS] embedding follow the information-bottleneck principle and are regularised with KL terms toward learnable Gaussian priors.
2. **Cross-view regularisation.** Each detection feature is perturbed with style statistics borrowed from another sample's generator feature.
3. **Discriminator-guided adaptation.** Pre-trained discriminators refine both branches and limit leakage between them.

On the MAGE benchmark, the method beats state-of-the-art detectors by up to 24.2% in accuracy and 26.2% in F1. Its advantage grows as more distinct generators are added to training. This matters because new LLMs appear faster than detectors can be retrained.

## Key points

- **Evaluation setup:** MAGE covers 20 LLMs grouped into 7 categories. Each test holds out one category and trains on the other six.
- **Ablation:** On held-out FLAN-T5, ACC/F1 rises from 60.9/52.6 (BERT baseline) to 68.9/64.1 (full model). On OPT, it rises from 82.1/84.2 to 89.1/88.3. The dual-bottleneck module contributes the most.
- **Robustness:** Compared with BERT, accuracy is higher by up to 46.18% under generator-style perturbations (GPT) and 17.98% under Gaussian noise (BigScience).
- **Representation analysis:** t-SNE plots show that the bottleneck encoder removes the per-generator clusters that a plain MLP encoder forms.
- **Limitations and code:** The authors note limited interpretability, sensitivity to hyperparameters, and no testing against adversarial attacks. Code is announced at github.com/PuXiao06/DRGD.

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

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works

## Cite

Cite as: Xiao Pu, Zepeng Cheng, Lin Yuan, Yu Wu and Xiuli Bi. 2026. Breaking the Generator Barrier: Disentangled Representation for Generalizable AI-Text Detection. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

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

```bibtex
@inproceedings{pu2026breaking,
  title = {{Breaking the Generator Barrier: Disentangled Representation for Generalizable AI-Text Detection}},
  author = {Xiao Pu, Zepeng Cheng, Lin Yuan, Yu Wu and Xiuli Bi},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.120},
  url = {https://doi.org/10.18653/v1/2026.acl-long.120}
}
```

- [← previous Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks](https://md.research.elamur.ai/free/en/papers/saha-2026-breaking-code-security-assessment-ai/)
- [next → Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents](https://md.research.elamur.ai/free/en/papers/wang-2026-breaking-impasse-dual-scale-evolutionary/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/24/)

## References

42 references, 16 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Josh Achiam and 1 others. 2023. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). arXiv preprint arXiv:2303.08774.
2. Anthropic. 2026. Introducing Claude Sonnet 4.6: Our fastest, smartest model is now available for all. [https://www.anthropic.com/news/](https://www.anthropic.com/news/) claude-sonnet-4-6. [↗](https://www.anthropic.com/news/)
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://md.research.elamur.ai/free/en/papers/bao-2023-fast-detectgpt-efficient-zero-shot/). In The Twelfth International Conference on Learning Representations.
4. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, and 1 others. 2020. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). Advances in neural information processing systems, 33:1877–1901.
5. Jiaqi Chen, Xiaoye Zhu, Tianyang Liu, Ying Chen, Chen Xinhui, Yiwen Yuan, Chak Tou Leong, Zuchao Li, Long Tang, Lei Zhang, and 1 others. 2025. Imitate before detect: Aligning machine stylistic preference for machine-revised text detection. In Proceedings of the AAAI Conference on Artificial Intellig… [find](https://scholar.google.com/scholar?q=Jiaqi+Chen%2C+Xiaoye+Zhu%2C+Tianyang+Liu%2C+Ying+Chen%2C+Chen+Xinhui%2C+Yiwen+Yuan%2C+Chak+Tou+Leong%2C+Zuchao+Li%2C+Long+Tang%2C+Lei+Zhang%2C+and+1+others%2E+2025%2E+Imitate+before+detect%3A+Aligning+machine+stylistic+prefere)
6. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. [Bert: Pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,…
7. Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario March, and Victor Lempitsky. 2016. Domain-adversarial training of neural networks. Journal of machine learning research, 17(59):1–35. [find](https://scholar.google.com/scholar?q=Yaroslav+Ganin%2C+Evgeniya+Ustinova%2C+Hana+Ajakan%2C+Pascal+Germain%2C+Hugo+Larochelle%2C+Fran%C3%A7ois+Laviolette%2C+Mario+March%2C+and+Victor+Lempitsky%2E+2016%2E+Domain%2Dadversarial+training+of+neural+networks%2E+Journal+o)
8. Ji Gao, Jack Lanchantin, Mary Lou Soffa, and Yanjun Qi. 2018. [Black-box generation of adversarial text sequences to evade deep learning classifiers](https://md.research.elamur.ai/free/en/papers/gao-2018-black-box-generation-adversarial-text/). In 2018 IEEE Security and Privacy Workshops (SPW), pages 50–56. IEEE.
9. Sebastian Gehrmann and 1 others. 2019. [Gltr: Statistical detection and visualization of generated text](https://md.research.elamur.ai/free/en/papers/gehrmann-2019-gltr-statistical-detection-visualization-generated/). In Proceedings of the 57th Annual Meeting ofthe Association for Computational Linguistics: System Demonstrations., pages 111–116.
10. Jiazhi Guan, Yi Zhao, Zhuoer Xu, Changhua Meng, Ke Xu, and Youjian Zhao. 2024. Adversarial robust safeguard for evading deep facial manipulation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 118–126. [find](https://scholar.google.com/scholar?q=Jiazhi+Guan%2C+Yi+Zhao%2C+Zhuoer+Xu%2C+Changhua+Meng%2C+Ke+Xu%2C+and+Youjian+Zhao%2E+2024%2E+Adversarial+robust+safeguard+for+evading+deep+facial+manipulation%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+In)
11. Hanxi Guo, Siyuan Cheng, Xiaolong Jin, Zhuo Zhang, Kaiyuan Zhang, Guanhong Tao, Guangyu Shen, and Xiangyu Zhang. 2024. Biscope: Ai-generated text detection by checking memorization of preceding tokens. Advances in Neural Information Processing Systems, 37:104065–104090. [find](https://scholar.google.com/scholar?q=Hanxi+Guo%2C+Siyuan+Cheng%2C+Xiaolong+Jin%2C+Zhuo+Zhang%2C+Kaiyuan+Zhang%2C+Guanhong+Tao%2C+Guangyu+Shen%2C+and+Xiangyu+Zhang%2E+2024%2E+Biscope%3A+Ai%2Dgenerated+text+detection+by+checking+memorization+of+preceding+tokens)
12. Beizhe Hu, Qiang Sheng, Juan Cao, Yuhui Shi, Yang Li, Danding Wang, and Peng Qi. 2024. Bad actor, good advisor: Exploring the role of large language models in fake news detection. In Proceedings of the AAAI conference on artificial intelligence, volume 38, pages 22105–22113. [find](https://scholar.google.com/scholar?q=Beizhe+Hu%2C+Qiang+Sheng%2C+Juan+Cao%2C+Yuhui+Shi%2C+Yang+Li%2C+Danding+Wang%2C+and+Peng+Qi%2E+2024%2E+Bad+actor%2C+good+advisor%3A+Exploring+the+role+of+large+language+models+in+fake+news+detection%2E+In+Proceedings+of+th)
13. Xiaomeng Hu and 1 others. 2023. Radar: Robust ai-text detection via adversarial learning. Advances in neural information processing systems, 36:15077– 15095. [find](https://scholar.google.com/scholar?q=Xiaomeng+Hu+and+1+others%2E+2023%2E+Radar%3A+Robust+ai%2Dtext+detection+via+adversarial+learning%2E+Advances+in+neural+information+processing+systems%2C+36%3A15077%E2%80%93+15095%2E)
14. Guanhua Huang, Yuchen Zhang, Zhe Li, Yongjian You, Mingze Wang, and Zhouwang Yang. 2024. Are ai-generated text detectors robust to adversarial perturbations? Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Guanhua+Huang%2C+Yuchen+Zhang%2C+Zhe+Li%2C+Yongjian+You%2C+Mingze+Wang%2C+and+Zhouwang+Yang%2E+2024%2E+Are+ai%2Dgenerated+text+detectors+robust+to+adversarial+perturbations%3F+Proceedings+of+the+62nd+Annual+Meeting+of+)
15. Zhiwei Jiang, Tianyi Gao, Yafeng Yin, Meng Liu, Hua Yu, Zifeng Cheng, and Qing Gu. 2023. Improving domain generalization for prompt-aware essay scoring via disentangled representation learning. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long… [find](https://scholar.google.com/scholar?q=Zhiwei+Jiang%2C+Tianyi+Gao%2C+Yafeng+Yin%2C+Meng+Liu%2C+Hua+Yu%2C+Zifeng+Cheng%2C+and+Qing+Gu%2E+2023%2E+Improving+domain+generalization+for+prompt%2Daware+essay+scoring+via+disentangled+representation+learning%2E+In+Pro)
16. Di Jin, Zhijing Jin, Joey Tianyi Zhou, and Peter Szolovits. 2020. [Is bert really robust? a strong baseline for natural language attack on text classification and entailment](https://md.research.elamur.ai/free/en/papers/jin-2019-bert-really-robust-strong-baseline/). In Proceedings of the AAAI conference on artificial intelligence, volume 34, pages 8018–8025.
17. Diederik P Kingma and Max Welling. 2013. [Autoencoding variational bayes](https://md.research.elamur.ai/free/en/papers/kingma-2013-auto-encoding-variational-bayes/). arXiv preprint arXiv:1312.6114.
18. John Kirchenbauer, Jonas Geiping, Yuxin Wen, Jonathan Katz, Ian Miers, and Tom Goldstein. 2023. [A watermark for large language models](https://md.research.elamur.ai/free/en/papers/kirchenbauer-2023-watermark-large-language-models/). In International Conference on Machine Learning, pages 17061–17084. PMLR.
19. Kalpesh Krishna, Yixiao Song, Marzena Karpinska, John Wieting, and Mohit Iyyer. 2023. [Paraphrasing evades detectors of ai-generated text, but retrieval is an effective defense](https://md.research.elamur.ai/free/en/papers/krishna-2023-paraphrasing-evades-detectors-ai-generated/). Advances in Neural Information Processing Systems, 36:27469–27500.
20. Xiaotong Li, Yongxing Dai, Yixiao Ge, Jun Liu, Ying Shan, and LINGYU DUAN. 2022. Uncertainty modeling for out-of-distribution generalization. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Xiaotong+Li%2C+Yongxing+Dai%2C+Yixiao+Ge%2C+Jun+Liu%2C+Ying+Shan%2C+and+LINGYU+DUAN%2E+2022%2E+Uncertainty+modeling+for+out%2Dof%2Ddistribution+generalization%2E+In+International+Conference+on+Learning+Representations%2E)
21. Ya Li, Mingming Gong, Xinmei Tian, Tongliang Liu, and Dacheng Tao. 2018. Domain generalization via conditional invariant representations. In Proceedings of the AAAI conference on artificial intelligence, volume 32. [find](https://scholar.google.com/scholar?q=Ya+Li%2C+Mingming+Gong%2C+Xinmei+Tian%2C+Tongliang+Liu%2C+and+Dacheng+Tao%2E+2018%2E+Domain+generalization+via+conditional+invariant+representations%2E+In+Proceedings+of+the+AAAI+conference+on+artificial+intelligen)
22. 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](https://md.research.elamur.ai/free/en/papers/li-2024-mage-machine-generated-text-detection/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 36–53, Bangk…
23. Yuanfan Li, Zhaohan Zhang, Chengzhengxu Li, Chao Shen, and Xiaoming Liu. 2025. Iron sharpens iron: Defending against attacks in machine-generated text detection with adversarial training. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Paper… [find](https://scholar.google.com/scholar?q=Yuanfan+Li%2C+Zhaohan+Zhang%2C+Chengzhengxu+Li%2C+Chao+Shen%2C+and+Xiaoming+Liu%2E+2025%2E+Iron+sharpens+iron%3A+Defending+against+attacks+in+machine%2Dgenerated+text+detection+with+adversarial+training%2E+In+Proceedin)
24. Aiwei Liu, Leyi Pan, Xuming Hu, Shuang Li, Lijie Wen, Irwin King, and Philip S. Yu. 2024a. An unforgeable publicly verifiable watermark for large language models. In The Twelfth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Aiwei+Liu%2C+Leyi+Pan%2C+Xuming+Hu%2C+Shuang+Li%2C+Lijie+Wen%2C+Irwin+King%2C+and+Philip+S%2E+Yu%2E+2024a%2E+An+unforgeable+publicly+verifiable+watermark+for+large+language+models%2E+In+The+Twelfth+International+Conferen)
25. Shengchao Liu, Xiaoming Liu, Yichen Wang, Zehua Cheng, Chengzhengxu Li, Zhaohan Zhang, Yu Lan, and Chao Shen. 2024b. [Does detectgpt fully utilize perturbation? bridging selective perturbation to fine-tuned contrastive learning detector would be better](https://md.research.elamur.ai/free/en/papers/liu-2024-does-detectgpt-fully-utilize-perturbation/). Proceedings of the 62nd Annual Meeting of the A…
26. Xue Bin Peng, Marcin Andrychowicz, Wojciech Zaremba, and Pieter Abbeel. 2018. Sim-to-real transfer of robotic control with dynamics randomization. In 2018 IEEE international conference on robotics and automation (ICRA), pages 3803–3810. IEEE. [find](https://scholar.google.com/scholar?q=Xue+Bin+Peng%2C+Marcin+Andrychowicz%2C+Wojciech+Zaremba%2C+and+Pieter+Abbeel%2E+2018%2E+Sim%2Dto%2Dreal+transfer+of+robotic+control+with+dynamics+randomization%2E+In+2018+IEEE+international+conference+on+robotics+and)
27. Xiao Pu, Hao Wu, Xiuli Bi, Yu Wu, and Xinbo Gao. 2025. Dear: Disentangled event-agnostic representation learning for early fake news detection. Transactions of the Association for Computational Linguistics, 13:343–356. [find](https://scholar.google.com/scholar?q=Xiao+Pu%2C+Hao+Wu%2C+Xiuli+Bi%2C+Yu+Wu%2C+and+Xinbo+Gao%2E+2025%2E+Dear%3A+Disentangled+event%2Dagnostic+representation+learning+for+early+fake+news+detection%2E+Transactions+of+the+Association+for+Computational+Lingui)
28. Shuhuai Ren, Yihe Deng, Kun He, and Wanxiang Che. 2019. [Generating natural language adversarial examples through probability weighted word saliency](https://md.research.elamur.ai/free/en/papers/ren-2019-generating-natural-language-adversarial-examples/). In Proceedings of the 57th annual meeting of the association for computational linguistics, pages 1085– 1097.
29. Rui Shao and 1 others. 2023. Detecting and grounding multi-modal media manipulation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6904–6913. [find](https://scholar.google.com/scholar?q=Rui+Shao+and+1+others%2E+2023%2E+Detecting+and+grounding+multi%2Dmodal+media+manipulation%2E+In+Proceedings+of+the+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+Recognition%2C+pages+6904%E2%80%936913%2E)
30. Yuhui Shi, Qiang Sheng, Juan Cao, Hao Mi, Beizhe Hu, and Danding Wang. 2024. Ten words only still help: Improving black-box ai-generated text detection via proxy-guided efficient re-sampling. Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence (IJCAI-24). [find](https://scholar.google.com/scholar?q=Yuhui+Shi%2C+Qiang+Sheng%2C+Juan+Cao%2C+Hao+Mi%2C+Beizhe+Hu%2C+and+Danding+Wang%2E+2024%2E+Ten+words+only+still+help%3A+Improving+black%2Dbox+ai%2Dgenerated+text+detection+via+proxy%2Dguided+efficient+re%2Dsampling%2E+Proceedi)
31. Eyal Shnarch, Ariel Gera, Alon Halfon, Lena Dankin, Leshem Choshen, Ranit Aharonov, and Noam Slonim. 2022. Cluster & tune: Boost cold start performance in text classification. In Annual Meeting of the Association for Computational Linguistics., page 7639–7653. [find](https://scholar.google.com/scholar?q=Eyal+Shnarch%2C+Ariel+Gera%2C+Alon+Halfon%2C+Lena+Dankin%2C+Leshem+Choshen%2C+Ranit+Aharonov%2C+and+Noam+Slonim%2E+2022%2E+Cluster+%26+tune%3A+Boost+cold+start+performance+in+text+classification%2E+In+Annual+Meeting+of+the)
32. Kanishka Silva, Ingo Frommholz, Burcu Can, Frédéric Blain, Raheem Sarwar, and Laura Ugolini. 2024. Forged-gan-bert: Authorship attribution for llm-generated forged novels. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: Student Research… [find](https://scholar.google.com/scholar?q=Kanishka+Silva%2C+Ingo+Frommholz%2C+Burcu+Can%2C+Fr%C3%A9d%C3%A9ric+Blain%2C+Raheem+Sarwar%2C+and+Laura+Ugolini%2E+2024%2E+Forged%2Dgan%2Dbert%3A+Authorship+attribution+for+llm%2Dgenerated+forged+novels%2E+In+Proceedings+of+the+18th+C)
33. Jinyan Su, Terry Yue Zhuo, Di Wang, and Preslav Nakov. 2023. [DetectLLM: Leveraging log rank information for zero-shot detection of machine-generated text](https://md.research.elamur.ai/free/en/papers/su-2023-detectllm-leveraging-log-rank-information/). In The 2023 Conference on Empirical Methods in Natural Language Processing.
34. Bryan E Tuck and Rakesh M Verma. 2026. Guided perturbation sensitivity (gps): Detecting adversarial text via embedding stability and word importance. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 40, pages 26019–26027. [find](https://scholar.google.com/scholar?q=Bryan+E+Tuck+and+Rakesh+M+Verma%2E+2026%2E+Guided+perturbation+sensitivity+%28gps%29%3A+Detecting+adversarial+text+via+embedding+stability+and+word+importance%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificia)
35. Adaku Uchendu, Thai Le, Kai Shu, and Dongwon Lee. 2020. [Authorship attribution for neural text generation](https://md.research.elamur.ai/free/en/papers/uchendu-2020-authorship-attribution-neural-text-generation/). In Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP), pages 8384–8395.
36. Christoforos Vasilatos, Manaar Alam, Talal Rahwan, Yasir Zaki, and Michail Maniatakos. 2023. Howkgpt: Investigating the detection of chatgpt-generated university student homework through context-aware perplexity analysis. arXiv preprint arXiv:2305.18226. — [arXiv:2305.18226](https://arxiv.org/abs/2305.18226) [find](https://scholar.google.com/scholar?q=Christoforos+Vasilatos%2C+Manaar+Alam%2C+Talal+Rahwan%2C+Yasir+Zaki%2C+and+Michail+Maniatakos%2E+2023%2E+Howkgpt%3A+Investigating+the+detection+of+chatgpt%2Dgenerated+university+student+homework+through+context%2Daware)
37. 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 Multilingual Black-… [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)
38. Zhenhua Wang and 1 others. 2025. A novel benford’s law-driven approach for detecting machine-generated text. ACM Transactions on Information Systems. [find](https://scholar.google.com/scholar?q=Zhenhua+Wang+and+1+others%2E+2025%2E+A+novel+benford%E2%80%99s+law%2Ddriven+approach+for+detecting+machine%2Dgenerated+text%2E+ACM+Transactions+on+Information+Systems%2E)
39. Wenjie Wei, Yanyue Zhang, Jinyan Li, Panfei Liu, and Deyu Zhou. 2025. Cross-domain fake news detection based on dual-granularity adversarial training. In Proceedings of the 31st International Conference on Computational Linguistics, pages 9407–9417. [find](https://scholar.google.com/scholar?q=Wenjie+Wei%2C+Yanyue+Zhang%2C+Jinyan+Li%2C+Panfei+Liu%2C+and+Deyu+Zhou%2E+2025%2E+Cross%2Ddomain+fake+news+detection+based+on+dual%2Dgranularity+adversarial+training%2E+In+Proceedings+of+the+31st+International+Conferen)
40. Junchao Wu, Shu Yang, Runzhe Zhan, Yulin Yuan, Lidia Sam Chao, and Derek Fai Wong. 2025. [A survey on llm-generated text detection: Necessity, methods, and future directions](https://md.research.elamur.ai/free/en/papers/wu-2025-survey-llm-generated-text-detection/). Computational Linguistics, 51(1):275–338.
41. Hongyi Zhou, Jin Zhu, Pingfan Su, Kai Ye, Ying Yang, Shakeel AOB Gavioli-Akilagun, and Chengchun Shi. 2025. Adadetectgpt: Adaptive detection of llm-generated text with statistical guarantees. The 39th Conference on Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Hongyi+Zhou%2C+Jin+Zhu%2C+Pingfan+Su%2C+Kai+Ye%2C+Ying+Yang%2C+Shakeel+AOB+Gavioli%2DAkilagun%2C+and+Chengchun+Shi%2E+2025%2E+Adadetectgpt%3A+Adaptive+detection+of+llm%2Dgenerated+text+with+statistical+guarantees%2E+The+39th)
42. Xiaowei Zhu, Yubing Ren, Yanan Cao, Xixun Lin, Fang Fang, and Yangxi Li. 2025. Reliably bounding false positives: A zero-shot machine-generated text detection framework via multiscaled conformal prediction. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (V… [find](https://scholar.google.com/scholar?q=Xiaowei+Zhu%2C+Yubing+Ren%2C+Yanan+Cao%2C+Xixun+Lin%2C+Fang+Fang%2C+and+Yangxi+Li%2E+2025%2E+Reliably+bounding+false+positives%3A+A+zero%2Dshot+machine%2Dgenerated+text+detection+framework+via+multiscaled+conformal+predi)

*Updated 1 November 2026*