TripPattern: A Pattern-based Text Watermarking Method for Large Language Models

• URL: http://arxiv.org/abs/2609.12472v1
• Date: Fri, 11 Sep 2026 06:14:17 GMT
• Title: TripPattern: A Pattern-based Text Watermarking Method for Large Language Models
• Abstract summary: TripPattern is a pattern-based watermarking framework for large language models (LLMs)<n>TripPattern divides the vocabulary into one neutral group and two pattern groups.<n>During generation, the model alternates token selection between the two pattern groups to embed detectable patterns, while neutral tokens are selected independently to improve flexibility and preserve naturalness.<n>For detection, TripPattern uses pattern-based statistical tests that provide interpretable p-values by measuring how often adjacent tokens alternate between the pattern groups.
• Score: 66.60718824378505
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text watermarking techniques have gained significant attention for identifying machine-generated text and mitigating risks from large language models (LLMs). Existing methods typically divide an LLM's vocabulary into green and red tokens, but encouraging generation toward green tokens can reduce text quality and naturalness. To address this, we propose TripPattern, a watermarking framework that formulates text watermarking as a pattern-based matching task using three vocabulary partitions. TripPattern divides the vocabulary into one neutral group and two pattern groups. During generation, the model alternates token selection between the two pattern groups to embed detectable patterns, while neutral tokens are selected independently to improve flexibility and preserve naturalness. For detection, TripPattern uses pattern-based statistical tests that provide interpretable p-values by measuring how often adjacent tokens alternate between the pattern groups. Theoretical analysis and empirical evaluations on four multilingual datasets show that TripPattern maintains LLM generation quality while achieving robust watermark detectability.

Related papers

• RepreGuard: Detecting LLM-Generated Text by Revealing Hidden Representation Patterns [50.401907401444404]
  Large language models (LLMs) are crucial for preventing misuse and building trustworthy AI systems.<n>We propose RepreGuard, an efficient statistics-based detection method.<n> Experimental results show that RepreGuard outperforms all baselines with average 94.92% AUROC on both in-distribution (ID) and OOD scenarios.
  arXiv  Detail & Related papers  (2025-08-18T17:59:15Z)
• Improving the Generation Quality of Watermarked Large Language Models via Word Importance Scoring [81.62249424226084]
  Token-level watermarking inserts watermarks in the generated texts by altering the token probability distributions. This watermarking algorithm alters the logits during generation, which can lead to a downgraded text quality. We propose to improve the quality of texts generated by a watermarked language model by Watermarking with Importance Scoring (WIS)
  arXiv  Detail & Related papers  (2023-11-16T08:36:00Z)
• Three Bricks to Consolidate Watermarks for Large Language Models [13.559357913735122]
  This research consolidates watermarks for large language models based on three theoretical and empirical considerations. First, we introduce new statistical tests that offer robust theoretical guarantees which remain valid even at low false-positive rates. Second, we compare the effectiveness of watermarks using classical benchmarks in the field of natural language processing, gaining insights into their real-world applicability.
  arXiv  Detail & Related papers  (2023-07-26T17:56:36Z)
• DPIC: Decoupling Prompt and Intrinsic Characteristics for LLM Generated Text Detection [56.513637720967566]
  Large language models (LLMs) can generate texts that pose risks of misuse, such as plagiarism, planting fake reviews on e-commerce platforms, or creating inflammatory false tweets. Existing high-quality detection methods usually require access to the interior of the model to extract the intrinsic characteristics. We propose to extract deep intrinsic characteristics of the black-box model generated texts.
  arXiv  Detail & Related papers  (2023-05-21T17:26:16Z)
• Stylized Data-to-Text Generation: A Case Study in the E-Commerce Domain [53.22419717434372]
  We propose a new task, namely stylized data-to-text generation, whose aim is to generate coherent text according to a specific style. This task is non-trivial, due to three challenges: the logic of the generated text, unstructured style reference, and biased training samples. We propose a novel stylized data-to-text generation model, named StyleD2T, comprising three components: logic planning-enhanced data embedding, mask-based style embedding, and unbiased stylized text generation.
  arXiv  Detail & Related papers  (2023-05-05T03:02:41Z)
• A Watermark for Large Language Models [84.95327142027183]
  We propose a watermarking framework for proprietary language models. The watermark can be embedded with negligible impact on text quality. It can be detected using an efficient open-source algorithm without access to the language model API or parameters.
  arXiv  Detail & Related papers  (2023-01-24T18:52:59Z)
• Towards Computationally Verifiable Semantic Grounding for Language Models [18.887697890538455]
  The paper conceptualizes the LM as a conditional model generating text given a desired semantic message formalized as a set of entity-relationship triples. It embeds the LM in an auto-encoder by feeding its output to a semantic fluency whose output is in the same representation domain as the input message. We show that our proposed approaches significantly improve on the greedy search baseline.
  arXiv  Detail & Related papers  (2022-11-16T17:35:52Z)
• Collocation2Text: Controllable Text Generation from Guide Phrases in Russian [0.0]
  Collocation2Text is a plug-and-play method for automatic controllable text generation in Russian. The method is based on two interacting models: the autoregressive language ruGPT-3 model and the autoencoding language ruRoBERTa model. Experiments on generating news articles using the proposed method showed its effectiveness for automatically generated fluent texts.
  arXiv  Detail & Related papers  (2022-06-18T17:10:08Z)
• Unsupervised learning of text line segmentation by differentiating coarse patterns [0.0]
  We present an unsupervised deep learning method that embeds document image patches to a compact Euclidean space where distances correspond to a coarse text line pattern similarity. Text line segmentation can be easily implemented using standard techniques with the embedded feature vectors. We evaluate the method qualitatively and quantitatively on several variants of text line segmentation datasets to demonstrate its effectivity.
  arXiv  Detail & Related papers  (2021-05-19T21:21:30Z)

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.