Elamur Research⌕
☰
home / papers / 2026 / GigaCheck: Detecting LLM-generated Content via Object-Centric Span Localization

GigaCheck: Detecting LLM-generated Content via Object-Centric Span Localization

Paper · 2026 · Irina Tolstykh, Aleksandra Tsybina, Sergey Yakubson et al.

Summary

As LLM output becomes harder to tell apart from human writing, detectors have fallen behind. They struggle most with co-authored texts, where human and machine passages are mixed. GigaCheck tackles two tasks. The first is document-level classification (human vs. machine). The second is span-level localization, which finds the AI-written segments inside a document. Both tasks share one backbone: Mistral-7B v0.3 fine-tuned with LoRA on a simple proxy classification task.

The core novelty is in localization. The authors treat generated spans like objects in computer vision. A DN-DAB-DETR detection head takes the backbone's token embeddings and directly predicts character-level intervals, given as a center and a width. This removes the usual step of grouping token labels after prediction, and it does not depend on sentence boundaries or document layout.

The method is tested on three localization benchmarks and three classification benchmarks, all in English. The shared backbone matches or beats earlier baselines. This suggests that object-detection architectures can transfer from images to text. The source code is publicly released.

Key points

  • Benchmarks: RoFT, RoFT-ChatGPT and TriBERT are used for span localization. TweepFake, TuringBench and MAGE are used for binary classification.
  • TweepFake: GigaCheck (Mistral-7B) reaches 0.943 accuracy, compared with 0.896 for RoBERTa.
  • TuringBench: machine-class F1 is 0.9966 on FAIR_wmt20 and 0.9709 on GPT-3.
  • MAGE:
    • Full split: AvgRec 0.96 and AUROC 0.99, against Longformer's 0.91 and 0.99.
    • Unseen domains plus unseen model: AvgRec 0.89, against 0.76 for Longformer.
    • Paraphrase attacks: gains are marginal (AvgRec 0.69 vs. 0.67).
  • Backbone scaling on MAGE: moving to 12B and 24B backbones adds only small gains. Qwen2.5-72B drops to AvgRec 0.8338, which the authors read as likely overfitting, so they keep the 7B model.
  • Detection head and code: among the DETR variants tested (DAB-DETR, DeformableDETR, CO-DETR), DN-DAB-DETR performed best. Code is at github.com/ai-forever/gigacheck.

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, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksComputer Vision and Pattern Recognition · 2,869 works

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 3,320 works

Cite

Cite as Irina Tolstykh, Aleksandra Tsybina, Sergey Yakubson, Aleksandr Gordeev, Vladimir Dokholyan and Maksim Kuprashevich. 2026. GigaCheck: Detecting LLM-generated Content via Object-Centric Span Localization. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.213

@inproceedings{tolstykh2026gigacheck,
  title = {{GigaCheck: Detecting LLM-generated Content via Object-Centric Span Localization}},
  author = {Irina Tolstykh, Aleksandra Tsybina, Sergey Yakubson, Aleksandr Gordeev, Vladimir Dokholyan and Maksim Kuprashevich},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.213},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.213}
}

References

74 references, 24 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Wissam Antoun, Virginie Mouilleron, Benoît Sagot, and Djamé Seddah. 2023. Towards a robust detection of language model generated text: Is chatgpt that easy to detect? arXiv preprint arXiv:2306.05871. find
  2. Iz Beltagy, Matthew E Peters, and Arman Cohan. 2020. Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150.
  3. Amrita Bhattacharjee and Huan Liu. 2024. Fighting fire with fire: can chatgpt detect ai-generated text? ACM SIGKDD Explorations Newsletter, 25(2):14–21. find
  4. 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,… — Language Models are Few-Shot Learners
  5. Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, and Sergey Zagoruyko. 2020. End-to-end object detection with transformers. In European conference on computer vision, pages 213–229. Springer.
  6. Souradip Chakraborty, Amrit Singh Bedi, Sicheng Zhu, Bang An, Dinesh Manocha, and Furong Huang. 2023. On the possibilities of ai-generated text detection. arXiv preprint arXiv:2304.04736. — [arXiv:2304.04736](https://arxiv.org/abs/2304.04736) find
  7. Peng-Jen Chen, Ann Lee, Changhan Wang, Naman Goyal, Angela Fan, Mary Williamson, and Jiatao Gu. 2020. Facebook ai’s wmt20 news translation task submission. arXiv preprint arXiv:2011.08298. find
  8. Joseph Cutler, Liam Dugan, Shreya Havaldar, and Adam Stein. 2021. Automatic detection of hybrid human-machine text boundaries. find
  9. Jacob Devlin. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.
  10. Liam Dugan, Daphne Ippolito, Arun Kirubarajan, Sherry Shi, and Chris Callison-Burch. 2023. Real or fake text?: Investigating human ability to detect boundaries between human-written and machine-generated text. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, pages 12763–1… find
  11. Tiziano Fagni, Fabrizio Falchi, Margherita Gambini, Antonio Martella, and Maurizio Tesconi. 2021. Tweepfake: About detecting deepfake tweets. Plos one, 16(5):e0251415. find
  12. Leon Fröhling and Arkaitz Zubiaga. 2021. Feature-based detection of automated language models: tackling gpt-2, gpt-3 and grover. PeerJ Computer Science, 7:e443. find
  13. Sebastian Gehrmann, Hendrik Strobelt, and Alexander M Rush. 2019. Gltr: Statistical detection and visualization of generated text. arXiv preprint arXiv:1906.04043.
  14. Aleksandr Gordeev, Vladimir Dokholyan, Irina Tolstykh, and Maksim Kuprashevich. 2024. Saliency-guided detr for moment retrieval and highlight detection. find
  15. Dijana Vukovic Grbic and Igor Dujlovic. 2023. Social engineering with chatgpt. In 2023 22nd International Symposium INFOTEH-JAHORINA (IN-FOTEH), pages 1–5. IEEE. find
  16. German Gritsai, Anastasia Voznyuk, Andrey Grabovoy, and Yury Chekhovich. 2024. Are ai detectors good enough? a survey on quality of datasets with machine-generated texts. arXiv preprint arXiv:2410.14677. — [arXiv:2410.14677](https://arxiv.org/abs/2410.14677) find
  17. 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. arXiv preprint arXiv:2301.07597.
  18. Hans WA Hanley and Zakir Durumeric. 2024. Machine-made media: Monitoring the mobilization of machine-generated articles on misinformation and mainstream news websites. In Proceedings of the International AAAI Conference on Web and Social Media, volume 18, pages 542–556. find
  19. Xiuquan Hou, Meiqin Liu, Senlin Zhang, Ping Wei, Badong Chen, and Xuguang Lan. 2024. Relation detr: Exploring explicit position relation prior for object detection. arXiv preprint arXiv:2407.11699. — [arXiv:2407.11699](https://arxiv.org/abs/2407.11699) find
  20. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685.
  21. Kuan-Chih Huang, Tsung-Han Wu, Hung-Ting Su, and Winston H Hsu. 2022. Monodtr: Monocular 3d object detection with depth-aware transformer. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 4012–4021. find
  22. Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Ye Jin Bang, Andrea Madotto, and Pascale Fung. 2023. Survey of hallucination in natural language generation. ACM Computing Surveys, 55(12):1–38.
  23. Armand Joulin, Edouard Grave, Piotr Bojanowski, and Tomas Mikolov. 2016. Bag of tricks for efficient text classification. arXiv preprint arXiv:1607.01759. find
  24. Enkelejda Kasneci, Kathrin Sessler, Stefan Küchemann, Maria Bannert, Daryna Dementieva, Frank Fischer, Urs Gasser, Georg Groh, Stephan Günnemann, Eyke Hüllermeier, Stephan Krusche, Gitta Kutyniok, Tilman Michaeli, Claudia Nerdel, Jürgen Pfeffer, Oleksandra Poquet, Michael Sailer, Albrecht Schmidt, T… — ChatGPT for Good? On Opportunities and Challenges of Large Language Models for Education
  25. Ryuto Koike, Masahiro Kaneko, and Naoaki Okazaki. 2024. Outfox: Llm-generated essay detection through in-context learning with adversarially generated examples. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 21258–21266. find
  26. Kalpesh Krishna, Yixiao Song, Marzena Karpinska, John Wieting, and Mohit Iyyer. 2024. Paraphrasing evades detectors of ai-generated text, but retrieval is an effective defense. Advances in Neural Information Processing Systems, 36.
  27. Laida Kushnareva, Daniil Cherniavskii, Vladislav Mikhailov, Ekaterina Artemova, Serguei Barannikov, Alexander Bernstein, Irina Piontkovskaya, Dmitri Piontkovski, and Evgeny Burnaev. 2021. Artificial text detection via examining the topology of attention maps. arXiv preprint arXiv:2109.04825. find
  28. Laida Kushnareva, Tatiana Gaintseva, Dmitry Abulkhanov, Kristian Kuznetsov, German Magai, Eduard Tulchinskii, Serguei Barannikov, Sergey Nikolenko, and Irina Piontkovskaya. Ai-generated text boundary detection with roft. In First Conference on Language Modeling. find
  29. Jie Lei, Tamara L Berg, and Mohit Bansal. 2021. Detecting moments and highlights in videos via natural language queries. Advances in Neural Information Processing Systems, 34:11846–11858. find
  30. Feng Li, Hao Zhang, Shilong Liu, Jian Guo, Lionel M Ni, and Lei Zhang. 2022. Dn-detr: Accelerate detr training by introducing query denoising. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 13619–13627. find
  31. 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.
  32. Yuanzhi Li, Sébastien Bubeck, Ronen Eldan, Allie Del Giorno, Suriya Gunasekar, and Yin Tat Lee. 2023. Textbooks are all you need ii: phi-1.5 technical report. arXiv preprint arXiv:2309.05463.
  33. T Lin. 2017. Focal loss for dense object detection. arXiv preprint arXiv:1708.02002.
  34. Shilong Liu, Feng Li, Hao Zhang, Xiao Yang, Xianbiao Qi, Hang Su, Jun Zhu, and Lei Zhang. 2022. Dab-detr: Dynamic anchor boxes are better queries for detr. arXiv preprint arXiv:2201.12329. — [arXiv:2201.12329](https://arxiv.org/abs/2201.12329) find
  35. Yikang Liu, Ziyin Zhang, Wanyang Zhang, Shisen Yue, Xiaojing Zhao, Xinyuan Cheng, Yiwen Zhang, and Hai Hu. 2023a. Argugpt: evaluating, understanding and identifying argumentative essays generated by gpt models. find
  36. Yinhan Liu. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692.
  37. Zeyan Liu, Zijun Yao, Fengjun Li, and Bo Luo. 2023b. Check me if you can: Detecting chatgpt-generated academic writing using checkgpt. arXiv preprint arXiv:2306.05524. — [arXiv:2306.05524](https://arxiv.org/abs/2306.05524) find
  38. Ilya Loshchilov and Frank Hutter. 2016. Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983. find
  39. Yisroel Mirsky, Ambra Demontis, Jaidip Kotak, Ram Shankar, Deng Gelei, Liu Yang, Xiangyu Zhang, Maura Pintor, Wenke Lee, Yuval Elovici, and Battista Biggio. 2023. The threat of offensive ai to organizations. Computers Security, 124:103006. find
  40. Eric Mitchell, Yoonho Lee, Alexander Khazatsky, Christopher D Manning, and Chelsea Finn. 2023. Detectgpt: Zero-shot machine-generated text detection using probability curvature. In International Conference on Machine Learning, pages 24950–24962. PMLR.
  41. WonJun Moon, Sangeek Hyun, SuBeen Lee, and Jae-Pil Heo. 2023. Correlation-guided query-dependency calibration for video temporal grounding. find
  42. OpenAI. 2023a. ChatGPT: A Large Language Model. Online; accessed February 13, 2024. Available at https://www.openai.com/. ↗
  43. OpenAI. 2023b. Gpt-4 technical report.
  44. Mike Perkins, Jasper Roe, Darius Postma, James Mc-Gaughran, and Don Hickerson. 2023. Game of tones: faculty detection of gpt-4 generated content in university assessments. arXiv preprint arXiv:2305.18081. — [arXiv:2305.18081](https://arxiv.org/abs/2305.18081) find
  45. Hamid Rezatofighi, Nathan Tsoi, JunYoung Gwak, Amir Sadeghian, Ian Reid, and Silvio Savarese. 2019. Generalized intersection over union: A metric and a loss for bounding box regression. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 658–666. find
  46. Sayak Saha Roy, Krishna Vamsi Naragam, and Shirin Nilizadeh. 2023. Generating phishing attacks using chatgpt. arXiv preprint arXiv:2305.05133. — [arXiv:2305.05133](https://arxiv.org/abs/2305.05133) find
  47. V Sanh. 2019. Distilbert, a distilled version of bert: Smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108. find
  48. Irene Solaiman, Miles Brundage, Jack Clark, Amanda Askell, Ariel Herbert-Voss, Jeff Wu, Alec Radford, Gretchen Krueger, Jong Wook Kim, Sarah Kreps, Miles McCain, Alex Newhouse, Jason Blazakis, Kris McGuffie, and Jasmine Wang. 2019. Release strategies and the social impacts of language models.
  49. Chris Stokel-Walker. 2022. Ai bot chatgpt writes smart essays-should academics worry? Nature. find
  50. Zeyan Liu, Zijun Yao, Fengjun Li, and Bo Luo. 2023c. On the detectability of chatgpt content: benchmarking, methodology, and evaluation through the lens of academic writing. arXiv e-prints, pages arXiv–2306. find
  51. Jinyan Su, Terry Yue Zhuo, Di Wang, and Preslav Nakov. 2023. Detectllm: Leveraging log rank information for zero-shot detection of machine-generated text. arXiv preprint arXiv:2306.05540.
  52. I Loshchilov. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101. find
  53. H Holden Thorp. 2023. Chatgpt is fun, but not an author. find
  54. Irina Tolstykh, Aleksandra Tsybina, Sergey Yakubson, and Maksim Kuprashevich. 2025. Llmtrace: A corpus for classification and fine-grained localization of ai-written text. find
  55. Eduard Tulchinskii, Kristian Kuznetsov, Laida Kushnareva, Daniil Cherniavskii, Sergey Nikolenko, Evgeny Burnaev, Serguei Barannikov, and Irina Piontkovskaya. 2024. Intrinsic dimension estimation for robust detection of ai-generated texts. Advances in Neural Information Processing Systems, 36.
  56. Adaku Uchendu, Thai Le, and Dongwon Lee. 2023. Toproberta: Topology-aware authorship attribution of deepfake texts. arXiv preprint arXiv:2309.12934. — [arXiv:2309.12934](https://arxiv.org/abs/2309.12934) find
  57. Adaku Uchendu, Thai Le, Kai Shu, and Dongwon Lee. 2020. Authorship attribution for neural text generation. In Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP), pages 8384–8395.
  58. Adaku Uchendu, Zeyu Ma, Thai Le, Rui Zhang, and Dongwon Lee. 2021. Turingbench: A benchmark environment for turing test in the age of neural text generation. arXiv preprint arXiv:2109.13296.
  59. Zhilin Yang. 2019. Xlnet: Generalized autoregressive pretraining for language understanding. arXiv preprint arXiv:1906.08237.
  60. Zhen Yin and Shenghua Wang. 2026. Span-level detection of ai-generated scientific text via contrastive learning and structural calibration. Knowledge-Based Systems, 334:115123. find
  61. Rowan Zellers, Ari Holtzman, Hannah Rashkin, Yonatan Bisk, Ali Farhadi, Franziska Roesner, and Yejin Choi. 2019. Defending against neural fake news. Advances in neural information processing systems, 32.
  62. Zijie Zeng, Shiqi Liu, Lele Sha, Zhuang Li, Kaixun Yang, Sannyuya Liu, Dragan Gašević, and Guanliang Chen. 2024a. Detecting ai-generated sentences in human-ai collaborative hybrid texts: Challenges, strategies, and insights. find
  63. Zijie Zeng, Lele Sha, Yuheng Li, Kaixun Yang, Dragan Gašević, and Guangliang Chen. 2024b. Towards automatic boundary detection for human-ai collaborative hybrid essay in education. find
  64. 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
  65. Chuhan Zhang, Ankush Gupta, and Andrew Zisserman. 2021. Temporal query networks for fine-grained video understanding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4486–4496. find
  66. Vivek Verma, Eve Fleisig, Nicholas Tomlin, and Dan Klein. 2023. Ghostbuster: Detecting text ghostwritten by large language models. arXiv preprint arXiv:2305.15047.
  67. Hao Zhang, Feng Li, Shilong Liu, Lei Zhang, Hang Su, Jun Zhu, Lionel M Ni, and Heung-Yeung Shum. 2022. Dino: Detr with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605. — [arXiv:2203.03605](https://arxiv.org/abs/2203.03605) find
  68. 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
  69. Yuxia Wang, Jonibek Mansurov, Petar Ivanov, Jinyan Su, Artem Shelmanov, Akim Tsvigun, Osama Mohammed Afzal, Tarek Mahmoud, Giovanni Puccetti, Thomas Arnold, Alham Aji, Nizar Habash, Iryna Gurevych, and Preslav Nakov. 2024. M4GTbench: Evaluation benchmark for black-box machine-generated text detectio… find
  70. Junchao Wu, Shu Yang, Runzhe Zhan, Yulin Yuan, Derek F Wong, and Lidia S Chao. 2023a. A survey on llm-gernerated text detection: Necessity, methods, and future directions. arXiv preprint arXiv:2310.14724. — [arXiv:2310.14724](https://arxiv.org/abs/2310.14724) find
  71. Qihui Zhang, Chujie Gao, Dongping Chen, Yue Huang, Yixin Huang, Zhenyang Sun, Shilin Zhang, Weiye Li, Zhengyan Fu, Yao Wan, and Lichao Sun. 2024. LLM-as-a-coauthor: Can mixed human-written and machine-generated text be detected? In Findings of the Association for Computational Linguistics: NAACL 202… find
  72. X Zhu, W Su, L Lu, B Li, X Wang, and J Dai. 2020. Deformable detr: Deformable transformers for end-to-end object detection. arxiv 2020. arXiv preprint arXiv:2010.04159. — [arXiv:2010.04159](https://arxiv.org/abs/2010.04159) find
  73. Zhuofan Zong, Guanglu Song, and Yu Liu. 2023. Detrs with collaborative hybrid assignments training. In Proceedings of the IEEE/CVF international conference on computer vision, pages 6748–6758. find
  74. Kangxi Wu, Liang Pang, Huawei Shen, Xueqi Cheng, and Tat-Seng Chua. 2023b. Llmdet: A third party large language models generated text detection tool. arXiv preprint arXiv:2305.15004. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/tolstykh-2026-gigacheck-detecting-llm-generated-content/