---
title: "Exons-Detect — paper by Zhu et al. (2026) — summary and ideas"
description: "Zero-shot detectors of machine-written text usually average per-token statistics into a single score. 31 references."
authors: ["Xiaowei Zhu", "Yubing Ren", "Fang Fang", "Shi Wang", "Yanan Cao", "Li Guo"]
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.1211/"
doi: "10.18653/v1/2026.acl-long.1211"
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/zhu-2026-exons-detect-identifying-amplifying-exonic/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhu-2026-exons-detect-identifying-amplifying-exonic/)

[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/32/) / Exons-Detect: Identifying and Amplifying Exonic Tokens via Hidden-State Discrepancy for Robust AI-Generated Text Detection

# Exons-Detect: Identifying and Amplifying Exonic Tokens via Hidden-State Discrepancy for Robust AI-Generated Text Detection

**Authors:** Xiaowei Zhu, [Yubing Ren](https://md.research.elamur.ai/free/en/authors/yubing-ren/), [Fang Fang](https://md.research.elamur.ai/free/en/authors/fang-fang/), [Shi Wang](https://md.research.elamur.ai/free/en/authors/shi-wang/), [Yanan Cao](https://md.research.elamur.ai/free/en/authors/yanan-cao/) and [Li Guo](https://md.research.elamur.ai/free/en/authors/li-guo/) · **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.1211/) · [PDF](https://aclanthology.org/2026.acl-long.1211.pdf) · [DOI 10.18653/v1/2026.acl-long.1211](https://doi.org/10.18653/v1/2026.acl-long.1211) · [OpenAlex](https://openalex.org/W7166838834)

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

## Summary
Zero-shot detectors of machine-written text usually average per-token statistics into a single score. This treats every token as equally useful, so the signal weakens on short inputs or after local edits. Exons-Detect is a training-free detector that weights tokens unequally, borrowing the exon/intron analogy from genetics.

The method runs the text through two paired proxy LLMs, such as an instruct model and its base version. For each token, it averages the cosine distance between the two models' hidden states across all layers. Tokens whose discrepancy exceeds a threshold θ are labelled "exonic" and receive extra weight through a nonlinear mapping with slope α. The weighted log-perplexity and cross-perplexity then form a "translation score," which is compared with a decision threshold. The scoring also uses DNA-DetectLLM's mutation-repair idea.

On public benchmarks including DetectRL, M4 and RealDet, the method reports state-of-the-art AUROC and stays robust under adversarial attacks and different text lengths. Its speed suits large-scale use.

## Key points
- The average AUROC on DetectRL is 2.2% higher in relative terms than the strongest baseline, DNA-DetectLLM. Evaluation covers 3 public benchmarks and 2 adversarial attack types.
- The method works with several proxy pairs, all averaging above 90% AUROC: Falcon-7B-Instruct/Falcon-7B, LLaMA-2-7B/LLaMA-7B, Mistral-v0.1-7B-Instruct/Mistral-v0.1-7B and LLaMA-3.2-1B-Instruct/LLaMA-3.2-1B. On DetectRL, the small LLaMA-3.2-1B pair scored 92.87%, while the Falcon pair scored 90.82%.
- In ablations, removing the nonlinear weight mapping lowers average AUROC by 1.0%. Removing the mutation-repair component lowers it by 4.4%.
- Results stay within about 1% when θ or α change. The best settings are θ ≈ 0.15, α ≥ 10 and all 32 hidden layers; cutting to 4 layers costs up to 3.1% relative AUROC.
- Processing a 300-token RealDet sample takes under 0.8 s, using two forward passes. Code and data are released on GitHub (Xiaoweizhu57/Exons-Detect).

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

## Institutions

- [Chinese Academy of Sciences](https://md.research.elamur.ai/free/en/government/chinese-academy-of-sciences/) — Government body, Beijing, China · 246 works · 24,951 citations
- [University of Chinese Academy of Sciences](https://md.research.elamur.ai/free/en/universities/university-of-chinese-academy-of-sciences/) — University, Beijing, China · 188 works · 8,743 citations
- [Institute of Information Engineering](https://md.research.elamur.ai/free/en/labs/institute-of-information-engineering/) — Research institute, Beijing, China · 41 works · 1,485 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works

## Cite

Cite as: Xiaowei Zhu, Yubing Ren, Fang Fang, Shi Wang, Yanan Cao and Li Guo. 2026. Exons-Detect: Identifying and Amplifying Exonic Tokens via Hidden-State Discrepancy for Robust AI-Generated 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{zhu2026exons,
  title = {{Exons-Detect: Identifying and Amplifying Exonic Tokens via Hidden-State Discrepancy for Robust AI-Generated Text Detection}},
  author = {Xiaowei Zhu, Yubing Ren, Fang Fang, Shi Wang, Yanan Cao and Li Guo},
  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.1211},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1211}
}
```

- [← previous Execution as Verification: Fine-Grained Self-Correcting Reasoning for Complex KBQA](https://md.research.elamur.ai/free/en/papers/zhang-2026-execution-as-verification-fine-grained/)
- [next → Expanding the Lexicon of Ge'ez Based African Languages: A Comparative Study of Amharic and Tigrinya](https://md.research.elamur.ai/free/en/papers/teklehaymanot-2026-expanding-lexicon-ge-ez-based/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/32/)

## References

31 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. David Ifeoluwa Adelani, Hao Thi Mai, Fuming Fang, Huy Hoang Nguyen, Junichi Yamagishi, and Isao Echizen. 2019. Generating sentiment-preserving fake online reviews using neural language models and their human- and machine-based detection. In International Conference on Advanced Information Networking… [find](https://scholar.google.com/scholar?q=David+Ifeoluwa+Adelani%2C+Hao+Thi+Mai%2C+Fuming+Fang%2C+Huy+Hoang+Nguyen%2C+Junichi+Yamagishi%2C+and+Isao+Echizen%2E+2019%2E+Generating+sentiment%2Dpreserving+fake+online+reviews+using+neural+language+models+and+thei)
2. Alim Al Ayub Ahmed, Ayman Aljabouh, Praveen Kumar Donepudi, and Myung Suh Choi. 2021. Detecting fake news using machine learning : A systematic literature review. Preprint, arXiv:2102.04458. — [arXiv:2102.04458](https://arxiv.org/abs/2102.04458) [find](https://scholar.google.com/scholar?q=Alim+Al+Ayub+Ahmed%2C+Ayman+Aljabouh%2C+Praveen+Kumar+Donepudi%2C+and+Myung+Suh+Choi%2E+2021%2E+Detecting+fake+news+using+machine+learning+%3A+A+systematic+literature+review%2E+Preprint%2C+arXiv%3A2102%2E04458%2E+%E2%80%94+%5BarXiv%3A)
3. Guangsheng Bao, Yanbin Zhao, Juncai He, and Yue Zhang. 2025. Glimpse: Enabling white-box methods to use proprietary models for zero-shot LLM-generated text detection. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Guangsheng+Bao%2C+Yanbin+Zhao%2C+Juncai+He%2C+and+Yue+Zhang%2E+2025%2E+Glimpse%3A+Enabling+white%2Dbox+methods+to+use+proprietary+models+for+zero%2Dshot+LLM%2Dgenerated+text+detection%2E+In+The+Thirteenth+International+C)
4. 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.
5. Souradip Chakraborty, Amrit Singh Bedi, Sicheng Zhu, Bang An, Dinesh Manocha, and Furong Huang. 2023. [find](https://scholar.google.com/scholar?q=Souradip+Chakraborty%2C+Amrit+Singh+Bedi%2C+Sicheng+Zhu%2C+Bang+An%2C+Dinesh+Manocha%2C+and+Furong+Huang%2E+2023%2E)
6. On the possibilities of ai-generated text detection. Preprint, arXiv:2304.04736. — [arXiv:2304.04736](https://arxiv.org/abs/2304.04736) [find](https://scholar.google.com/scholar?q=On+the+possibilities+of+ai%2Dgenerated+text+detection%2E+Preprint%2C+arXiv%3A2304%2E04736%2E+%E2%80%94+%5BarXiv%3A2304%2E04736%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2304%2E04736%29)
7. Xin Chen, Junchao Wu, Shu Yang, Runzhe Zhan, Zeyu Wu, Ziyang Luo, Di Wang, Min Yang, Lidia S. Chao, and Derek F. Wong. 2025. Repreguard: Detecting llm-generated text by revealing hidden representation patterns. Preprint, arXiv:2508.13152. [find](https://scholar.google.com/scholar?q=Xin+Chen%2C+Junchao+Wu%2C+Shu+Yang%2C+Runzhe+Zhan%2C+Zeyu+Wu%2C+Ziyang+Luo%2C+Di+Wang%2C+Min+Yang%2C+Lidia+S%2E+Chao%2C+and+Derek+F%2E+Wong%2E+2025%2E+Repreguard%3A+Detecting+llm%2Dgenerated+text+by+revealing+hidden+representation)
8. Elizabeth Clark, Tal August, Sofia Serrano, Nikita Haduong, Suchin Gururangan, and Noah A. Smith. 2021. All that’s ‘human’ is not gold: Evaluating human evaluation of generated text. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International… [find](https://scholar.google.com/scholar?q=Elizabeth+Clark%2C+Tal+August%2C+Sofia+Serrano%2C+Nikita+Haduong%2C+Suchin+Gururangan%2C+and+Noah+A%2E+Smith%2E+2021%2E+All+that%E2%80%99s+%E2%80%98human%E2%80%99+is+not+gold%3A+Evaluating+human+evaluation+of+generated+text%2E+In+Proceedings+of)
9. Sebastian Gehrmann, Hendrik Strobelt, and Alexander Rush. 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 of the Association for Computational Linguistics: System Demonstrations, pages 111–116, Florence, Italy. Association for Computat…
10. 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://md.research.elamur.ai/free/en/papers/guo-2023-close-chatgpt-human-experts-comparison/). Preprint, arXiv:2301.07597.
11. Hanxi Guo, Siyuan Cheng, Xiaolong Jin, Zhuo Zhang, Kaiyuan Zhang, Guanhong Tao, Guangyu Shen, and Xiangyu Zhang. 2024a. Biscope: Ai-generated text detection by checking memorization of preceding tokens. In Advances in Neural Information Processing Systems, volume 37, pages 104065–104090. Curran Asso… [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+2024a%2E+Biscope%3A+Ai%2Dgenerated+text+detection+by+checking+memorization+of+preceding+token)
12. Xun Guo, Shan Zhang, Yongxin He, Ting Zhang, Wanquan Feng, Haibin Huang, and Chongyang Ma. 2024b. Detective: Detecting ai-generated text via multi-level contrastive learning. In Advances in Neural Information Processing Systems, volume 37, pages 88320–88347. Curran Associates, Inc. [find](https://scholar.google.com/scholar?q=Xun+Guo%2C+Shan+Zhang%2C+Yongxin+He%2C+Ting+Zhang%2C+Wanquan+Feng%2C+Haibin+Huang%2C+and+Chongyang+Ma%2E+2024b%2E+Detective%3A+Detecting+ai%2Dgenerated+text+via+multi%2Dlevel+contrastive+learning%2E+In+Advances+in+Neural+Inf)
13. Zhiwei Guo, Yu Shen, Ali Kashif Bashir, Muhammad Imran, Neeraj Kumar, Di Zhang, and Keping Yu. 2021. Robust spammer detection using collaborative neural network in internet-of-things applications. IEEE Internet of Things Journal, 8(12):9549–9558. [find](https://scholar.google.com/scholar?q=Zhiwei+Guo%2C+Yu+Shen%2C+Ali+Kashif+Bashir%2C+Muhammad+Imran%2C+Neeraj+Kumar%2C+Di+Zhang%2C+and+Keping+Yu%2E+2021%2E+Robust+spammer+detection+using+collaborative+neural+network+in+internet%2Dof%2Dthings+applications%2E+IEE)
14. 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](https://md.research.elamur.ai/free/en/papers/hans-2024-spotting-llms-binoculars-zero-shot/).
15. Tatsunori B. Hashimoto, Hugh Zhang, and Percy Liang. 2019. [Unifying human and statistical evaluation for natural language generation](https://md.research.elamur.ai/free/en/papers/hashimoto-2019-unifying-human-statistical-evaluation-natural/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and…
16. Yongxin He, Shan Zhang, Yixuan Cao, Lei Ma, and Ping Luo. 2025. DETree: DEtecting human-AI collaborative texts via tree-structured hierarchical representation learning. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Yongxin+He%2C+Shan+Zhang%2C+Yixuan+Cao%2C+Lei+Ma%2C+and+Ping+Luo%2E+2025%2E+DETree%3A+DEtecting+human%2DAI+collaborative+texts+via+tree%2Dstructured+hierarchical+representation+learning%2E+In+The+Thirty%2Dninth+Annual+Conf)
17. Xiaomeng Hu, Pin-Yu Chen, and Tsung-Yi Ho. 2023. [Radar: Robust ai-text detection via adversarial learning](https://md.research.elamur.ai/free/en/papers/hu-2023-radar-robust-ai-text-detection/). In Advances in Neural Information Processing Systems, volume 36, pages 15077–15095. Curran Associates, Inc.
18. Daphne Ippolito, Daniel Duckworth, Chris Callison-Burch, and Douglas Eck. 2020. [Automatic detection of generated text is easiest when humans are fooled](https://md.research.elamur.ai/free/en/papers/ippolito-2019-automatic-detection-generated-text-easiest/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1808–1822, Online. Association for Computational…
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/). In Advances in Neural Information Processing Systems, volume 36, pages 27469– 27500. Curran Associates, Inc.
20. Runheng Liu, Heyan Huang, Xingchen Xiao, and Zhijing Wu. 2025. Zero-shot detection of LLM-generated text via implicit reward model. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Runheng+Liu%2C+Heyan+Huang%2C+Xingchen+Xiao%2C+and+Zhijing+Wu%2E+2025%2E+Zero%2Dshot+detection+of+LLM%2Dgenerated+text+via+implicit+reward+model%2E+In+The+Thirty%2Dninth+Annual+Conference+on+Neural+Information+Processi)
21. Eric Mitchell, Yoonho Lee, Alexander Khazatsky, Christopher D Manning, and Chelsea Finn. 2023. [DetectGPT: Zero-shot machine-generated text detection using probability curvature](https://md.research.elamur.ai/free/en/papers/mitchell-2023-detectgpt-zero-shot-machine-generated/). In Proceedings of the 40th International Conference on Machine Learning, volume 202 of Proceedings of Machine Learning Res…
22. Guilherme Penedo, Quentin Malartic, Daniel Hesslow, Ruxandra Cojocaru, Alessandro Cappelli, Hamza Alobeidli, Baptiste Pannier, Ebtesam Almazrouei, and Julien Launay. 2023. The RefinedWeb dataset for Falcon LLM: outperforming curated corpora with web data, and web data only. arXiv preprint arXiv:2306… [find](https://scholar.google.com/scholar?q=Guilherme+Penedo%2C+Quentin+Malartic%2C+Daniel+Hesslow%2C+Ruxandra+Cojocaru%2C+Alessandro+Cappelli%2C+Hamza+Alobeidli%2C+Baptiste+Pannier%2C+Ebtesam+Almazrouei%2C+and+Julien+Launay%2E+2023%2E+The+RefinedWeb+dataset+for+F)
23. Irene Solaiman, Miles Brundage, Jack Clark, Amanda Askell, Ariel Herbert-Voss, Jeff Wu, Alec Radford, Gretchen Krueger, Jong Wook Kim, Sarah Kreps, and 1 others. 2019. [Release strategies and the social impacts of language models](https://md.research.elamur.ai/free/en/papers/solaiman-2019-release-strategies-social-impacts-language/). arXiv preprint arXiv:1908.09203.
24. Yiliao Song, Zhenqiao Yuan, Shuhai Zhang, Zhen Fang, Jun Yu, and Feng Liu. 2025. Deep kernel relative test for machine-generated text detection. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Yiliao+Song%2C+Zhenqiao+Yuan%2C+Shuhai+Zhang%2C+Zhen+Fang%2C+Jun+Yu%2C+and+Feng+Liu%2E+2025%2E+Deep+kernel+relative+test+for+machine%2Dgenerated+text+detection%2E+In+The+Thirteenth+International+Conference+on+Learning+)
25. Yuchuan Tian, Hanting Chen, Xutao Wang, Zheyuan Bai, QINGHUA ZHANG, Ruifeng Li, Chao Xu, and Yunhe Wang. 2024. Multiscale positive-unlabeled detection of AI-generated texts. In The Twelfth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Yuchuan+Tian%2C+Hanting+Chen%2C+Xutao+Wang%2C+Zheyuan+Bai%2C+QINGHUA+ZHANG%2C+Ruifeng+Li%2C+Chao+Xu%2C+and+Yunhe+Wang%2E+2024%2E+Multiscale+positive%2Dunlabeled+detection+of+AI%2Dgenerated+texts%2E+In+The+Twelfth+Internation)
26. 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, Online. Association for Computational Linguistics.
27. 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)
28. Junchao Wu, Runzhe Zhan, Derek F. Wong, Shu Yang, Xinyi Yang, Yulin Yuan, and Lidia S. Chao. 2024. DetectRL: Benchmarking LLM-generated text detection in real-world scenarios. In The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track. [find](https://scholar.google.com/scholar?q=Junchao+Wu%2C+Runzhe+Zhan%2C+Derek+F%2E+Wong%2C+Shu+Yang%2C+Xinyi+Yang%2C+Yulin+Yuan%2C+and+Lidia+S%2E+Chao%2E+2024%2E+DetectRL%3A+Benchmarking+LLM%2Dgenerated+text+detection+in+real%2Dworld+scenarios%2E+In+The+Thirty%2Deight+Conf)
29. Yihuai Xu, Yongwei Wang, Yifei Bi, Huangsen Cao, Zhouhan Lin, Yu Zhao, and Fei Wu. 2024. Training-free llm-generated text detection by mining token probability sequences. CoRR, abs/2410.06072. — [arXiv:2410.06072](https://arxiv.org/abs/2410.06072) [find](https://scholar.google.com/scholar?q=Yihuai+Xu%2C+Yongwei+Wang%2C+Yifei+Bi%2C+Huangsen+Cao%2C+Zhouhan+Lin%2C+Yu+Zhao%2C+and+Fei+Wu%2E+2024%2E+Training%2Dfree+llm%2Dgenerated+text+detection+by+mining+token+probability+sequences%2E+CoRR%2C+abs%2F2410%2E06072%2E+%E2%80%94+%5BarXi)
30. Xiaowei Zhu, Yubing Ren, Yanan Cao, Xixun Lin, Fang Fang, and Yangxi Li. 2025a. 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 (… [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+2025a%2E+Reliably+bounding+false+positives%3A+A+zero%2Dshot+machine%2Dgenerated+text+detection+framework+via+multiscaled+conformal+pred)
31. Xiaowei Zhu, Yubing Ren, Fang Fang, Qingfeng Tan, Shi Wang, and Yanan Cao. 2025b. DNA-detectLLM: Unveiling AI-generated text via a DNA-inspired mutation-repair paradigm. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Xiaowei+Zhu%2C+Yubing+Ren%2C+Fang+Fang%2C+Qingfeng+Tan%2C+Shi+Wang%2C+and+Yanan+Cao%2E+2025b%2E+DNA%2DdetectLLM%3A+Unveiling+AI%2Dgenerated+text+via+a+DNA%2Dinspired+mutation%2Drepair+paradigm%2E+In+The+Thirty%2Dninth+Annual+Con)

*Updated 2 November 2026*