Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detection

• URL: http://arxiv.org/abs/2412.10432v2
• Date: Sun, 22 Dec 2024 15:47:50 GMT
• Title: Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detection
• Authors: Jiaqi Chen, Xiaoye Zhu, Tianyang Liu, Ying Chen, Xinhui Chen, Yiwen Yuan, Chak Tou Leong, Zuchao Li, Tang Long, Lei Zhang, Chenyu Yan, Guanghao Mei, Jie Zhang, Lefei Zhang,
• Abstract summary: Large Language Models (LLMs) have revolutionized text generation. detecting machine-generated text increasingly challenging. We propose the "Imitate Before Detect" (ImBD) approach, which first imitates the machine-style token distribution. We then compare the distribution of the text to be tested with the machine-style distribution to determine whether the text has been machine-revised.
• Score: 39.62360229183229
• License:
• Abstract: Large Language Models (LLMs) have revolutionized text generation, making detecting machine-generated text increasingly challenging. Although past methods have achieved good performance on detecting pure machine-generated text, those detectors have poor performance on distinguishing machine-revised text (rewriting, expansion, and polishing), which can have only minor changes from its original human prompt. As the content of text may originate from human prompts, detecting machine-revised text often involves identifying distinctive machine styles, e.g., worded favored by LLMs. However, existing methods struggle to detect machine-style phrasing hidden within the content contributed by humans. We propose the "Imitate Before Detect" (ImBD) approach, which first imitates the machine-style token distribution, and then compares the distribution of the text to be tested with the machine-style distribution to determine whether the text has been machine-revised. To this end, we introduce style preference optimization (SPO), which aligns a scoring LLM model to the preference of text styles generated by machines. The aligned scoring model is then used to calculate the style-conditional probability curvature (Style-CPC), quantifying the log probability difference between the original and conditionally sampled texts for effective detection. We conduct extensive comparisons across various scenarios, encompassing text revisions by six LLMs, four distinct text domains, and three machine revision types. Compared to existing state-of-the-art methods, our method yields a 13% increase in AUC for detecting text revised by open-source LLMs, and improves performance by 5% and 19% for detecting GPT-3.5 and GPT-4o revised text, respectively. Notably, our method surpasses the commercially trained GPT-Zero with just $1,000$ samples and five minutes of SPO, demonstrating its efficiency and effectiveness.

Related papers

• RKadiyala at SemEval-2024 Task 8: Black-Box Word-Level Text Boundary Detection in Partially Machine Generated Texts [0.0]
  This paper introduces few reliable approaches for identifying which part of a given text is machine generated at a word level. We present a comparison with proprietary systems, performance of our model on unseen domains' and generators' texts. The findings reveal significant improvements in detection accuracy along with comparison on other aspects of detection capabilities.
  arXiv  Detail & Related papers  (2024-10-22T03:21:59Z)
• Detecting Machine-Generated Long-Form Content with Latent-Space Variables [54.07946647012579]
  Existing zero-shot detectors primarily focus on token-level distributions, which are vulnerable to real-world domain shifts. We propose a more robust method that incorporates abstract elements, such as event transitions, as key deciding factors to detect machine versus human texts.
  arXiv  Detail & Related papers  (2024-10-04T18:42:09Z)
• LLM-DetectAIve: a Tool for Fine-Grained Machine-Generated Text Detection [87.43727192273772]
  It is often hard to tell whether a piece of text was human-written or machine-generated. We present LLM-DetectAIve, designed for fine-grained detection. It supports four categories: (i) human-written, (ii) machine-generated, (iii) machine-written, then machine-humanized, and (iv) human-written, then machine-polished.
  arXiv  Detail & Related papers  (2024-08-08T07:43:17Z)
• Deciphering Textual Authenticity: A Generalized Strategy through the Lens of Large Language Semantics for Detecting Human vs. Machine-Generated Text [8.290557547578146]
  We introduce a novel system, T5LLMCipher, for detecting machine-generated text using a pretrained T5 encoder combined with LLM embedding sub-clustering. We find that our approach provides state-of-the-art generalization ability, with an average increase in F1 score on machine-generated text of 19.6% on unseen generators and domains.
  arXiv  Detail & Related papers  (2024-01-17T18:45:13Z)
• DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text [82.5469544192645]
  We propose a novel training-free detection strategy called Divergent N-Gram Analysis (DNA-GPT) By analyzing the differences between the original and new remaining parts through N-gram analysis, we unveil significant discrepancies between the distribution of machine-generated text and human-written text. Results show that our zero-shot approach exhibits state-of-the-art performance in distinguishing between human and GPT-generated text.
  arXiv  Detail & Related papers  (2023-05-27T03:58:29Z)
• Smaller Language Models are Better Black-box Machine-Generated Text Detectors [56.36291277897995]
  Small and partially-trained models are better universal text detectors. We find that whether the detector and generator were trained on the same data is not critically important to the detection success. For instance, the OPT-125M model has an AUC of 0.81 in detecting ChatGPT generations, whereas a larger model from the GPT family, GPTJ-6B, has AUC of 0.45.
  arXiv  Detail & Related papers  (2023-05-17T00:09:08Z)
• Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense [56.077252790310176]
  We present a paraphrase generation model (DIPPER) that can paraphrase paragraphs, condition on surrounding context, and control lexical diversity and content reordering. Using DIPPER to paraphrase text generated by three large language models (including GPT3.5-davinci-003) successfully evades several detectors, including watermarking. We introduce a simple defense that relies on retrieving semantically-similar generations and must be maintained by a language model API provider.
  arXiv  Detail & Related papers  (2023-03-23T16:29:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.