Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
80 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

CoCo: Coherence-Enhanced Machine-Generated Text Detection Under Data Limitation With Contrastive Learning (2212.10341v2)

Published 20 Dec 2022 in cs.CL

Abstract: Machine-Generated Text (MGT) detection, a task that discriminates MGT from Human-Written Text (HWT), plays a crucial role in preventing misuse of text generative models, which excel in mimicking human writing style recently. Latest proposed detectors usually take coarse text sequences as input and fine-tune pretrained models with standard cross-entropy loss. However, these methods fail to consider the linguistic structure of texts. Moreover, they lack the ability to handle the low-resource problem which could often happen in practice considering the enormous amount of textual data online. In this paper, we present a coherence-based contrastive learning model named CoCo to detect the possible MGT under low-resource scenario. To exploit the linguistic feature, we encode coherence information in form of graph into text representation. To tackle the challenges of low data resource, we employ a contrastive learning framework and propose an improved contrastive loss for preventing performance degradation brought by simple samples. The experiment results on two public datasets and two self-constructed datasets prove our approach outperforms the state-of-art methods significantly. Also, we surprisingly find that MGTs originated from up-to-date LLMs could be easier to detect than these from previous models, in our experiments. And we propose some preliminary explanations for this counter-intuitive phenomena. All the codes and datasets are open-sourced.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (68)
  1. Generating sentiment-preserving fake online reviews using neural language models and their human-and machine-based detection. In International Conference on Advanced Information Networking and Applications, pages 1341–1354. Springer.
  2. Computing locally coherent discourses. In Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL-04), pages 399–406.
  3. Palm 2 technical report. arXiv preprint arXiv:2305.10403.
  4. Real or fake? learning to discriminate machine from human generated text. arXiv preprint arXiv:1906.03351.
  5. Pythia: A suite for analyzing large language models across training and scaling. arXiv preprint arXiv:2304.01373.
  6. Gpt-neox-20b: An open-source autoregressive language model. arXiv preprint arXiv:2204.06745.
  7. Roi Blanco and Christina Lioma. 2011. Graph-based term weighting for information retrieval. Information Retrieval, 15:54–92.
  8. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901.
  9. Are all negatives created equal in contrastive instance discrimination? arXiv preprint arXiv:2010.06682.
  10. Dual contrastive learning: Text classification via label-aware data augmentation. arXiv preprint arXiv:2201.08702.
  11. Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297.
  12. Gpt-sentinel: Distinguishing human and chatgpt generated content. arXiv preprint arXiv:2305.07969.
  13. Making pre-trained language models better few-shot learners. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 3816–3830.
  14. Simcse: Simple contrastive learning of sentence embeddings. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6894–6910.
  15. Gltr: Statistical detection and visualization of generated text. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 111–116.
  16. Fake news on twitter during the 2016 us presidential election. Science, 363(6425):374–378.
  17. Barbara J Grosz and Candace L Sidner. 1986. Attention, intentions, and the structure of discourse. Computational linguistics, 12(3):175–204.
  18. Supervised contrastive learning for pre-trained language model fine-tuning. In International Conference on Learning Representations.
  19. How close is chatgpt to human experts? comparison corpus, evaluation, and detection. arXiv preprint arXiv:2301.07597.
  20. Momentum contrast for unsupervised visual representation learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 9729–9738.
  21. Mgtbench: Benchmarking machine-generated text detection. arXiv preprint arXiv:2303.14822.
  22. Graph ensemble learning over multiple dependency trees for aspect-level sentiment classification. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2884–2894.
  23. Eduard H Hovy. 1988. Planning coherent multisentential text. In Proceedings of the 26th annual meeting on Association for Computational Linguistics, pages 163–169.
  24. Binxuan Huang and Kathleen M Carley. 2019. Syntax-aware aspect level sentiment classification with graph attention networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 5469–5477.
  25. Faking fake news for real fake news detection: Propaganda-loaded training data generation. ArXiv, abs/2203.05386.
  26. Automatic detection of generated text is easiest when humans are fooled. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1808–1822.
  27. Nikiforos Karamanis and Hisar Maruli Manurung. 2002. Stochastic text structuring using the principle of continuity. In Proceedings of the International Natural Language Generation Conference, pages 81–88.
  28. Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL-HLT, pages 4171–4186.
  29. Ctrl: A conditional transformer language model for controllable generation. arXiv preprint arXiv:1909.05858.
  30. Mirella Lapata. 2003. Probabilistic text structuring: Experiments with sentence ordering. In ACL, volume 3, pages 545–552. Citeseer.
  31. Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7871–7880.
  32. Tensor graph convolutional networks for text classification. In Proceedings of the AAAI conference on artificial intelligence, volume 34, pages 8409–8416.
  33. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692.
  34. Ilya Loshchilov and Frank Hutter. 2018. Decoupled weight decay regularization. In International Conference on Learning Representations.
  35. Few-shot bot: Prompt-based learning for dialogue systems. ArXiv, abs/2110.08118.
  36. Coherence boosting: When your pretrained language model is not paying enough attention. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8214–8236, Dublin, Ireland. Association for Computational Linguistics.
  37. Fragkiskos D Malliaros and Konstantinos Skianis. 2015. Graph-based term weighting for text categorization. In Proceedings of the 2015 IEEE/ACM international conference on advances in social networks analysis and mining 2015, pages 1473–1479.
  38. William C Mann and Sandra A Thompson. 1987. Rhetorical structure theory: A theory of text organization. University of Southern California, Information Sciences Institute Los Angeles.
  39. Experiments using stochastic search for text planning. In Proceedings of the 9th International General Workshop, pages 98–107. ACL Anthology.
  40. Rada Mihalcea and Paul Tarau. 2004. Textrank: Bringing order into text. In Proceedings of the 2004 conference on empirical methods in natural language processing, pages 404–411.
  41. Smaller language models are better black-box machine-generated text detectors. arXiv preprint arXiv:2305.09859.
  42. Detectgpt: Zero-shot machine-generated text detection using probability curvature. arXiv preprint arXiv:2301.11305.
  43. Timothy Niven and Hung-Yu Kao. 2019. Probing neural network comprehension of natural language arguments. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4658–4664.
  44. OpenAI. 2023. Gpt-4 technical report. ArXiv, abs/2303.08774.
  45. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35:27730–27744.
  46. Semi-supervised sequence tagging with bidirectional language models. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1756–1765.
  47. On the zero-shot generalization of machine-generated text detectors. arXiv preprint arXiv:2310.05165.
  48. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9.
  49. Exploring the limits of transfer learning with a unified text-to-text transformer. The Journal of Machine Learning Research, 21(1):5485–5551.
  50. Release strategies and the social impacts of language models. arXiv preprint arXiv:1908.09203.
  51. Supervised prototypical contrastive learning for emotion recognition in conversation. arXiv preprint arXiv:2210.08713.
  52. Tacl: Improving bert pre-training with token-aware contrastive learning. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 2497–2507.
  53. Improving language generation with sentence coherence objective. arXiv preprint arXiv:2009.06358.
  54. Axiomatic attribution for deep networks. In International conference on machine learning, pages 3319–3328. PMLR.
  55. Spammer behavior analysis and detection in user generated content on social networks. In 2012 IEEE 32nd International Conference on Distributed Computing Systems, pages 305–314. IEEE.
  56. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971.
  57. Peter D Turney. 2002. Learning to extract keyphrases from text. arXiv preprint cs/0212013.
  58. Characterizing man-made vs. machine-made chatbot dialogs. In TTO.
  59. Authorship attribution for neural text generation. In Conf. on Empirical Methods in Natural Language Processing (EMNLP).
  60. Turingbench: A benchmark environment for turing test in the age of neural text generation. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 2001–2016.
  61. Ben Wang and Aran Komatsuzaki. 2021. GPT-J-6B: A 6 Billion Parameter Autoregressive Language Model. https://github.com/kingoflolz/mesh-transformer-jax.
  62. Feng Wang and Huaping Liu. 2021. Understanding the behaviour of contrastive loss. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 2495–2504.
  63. Max Welling and Thomas N Kipf. 2016. Semi-supervised classification with graph convolutional networks. In J. International Conference on Learning Representations (ICLR 2017).
  64. Fake news detection with generated comments for news articles. In 2020 IEEE 24th International Conference on Intelligent Engineering Systems (INES), pages 85–90. IEEE.
  65. Xlnet: Generalized autoregressive pretraining for language understanding. Advances in neural information processing systems, 32.
  66. Graph convolutional networks for text classification. In Proceedings of the AAAI conference on artificial intelligence, volume 33, pages 7370–7377.
  67. Defending against neural fake news. Advances in neural information processing systems, 32.
  68. Neural deepfake detection with factual structure of text. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2461–2470.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Xiaoming Liu (145 papers)
  2. Zhaohan Zhang (11 papers)
  3. Yichen Wang (61 papers)
  4. Hang Pu (1 paper)
  5. Yu Lan (22 papers)
  6. Chao Shen (168 papers)
Citations (35)
View on Semantic Scholar