mlsanityData to 7 Oct 2026

MarkLLM: An Open-Source Toolkit for LLM Watermarking

arXiv 2405.10051 ↗First posted 16 May 2024cs.CR cs.CLcited by 80

On the map: LLM safety and security → Watermarking generated content and models

Abstract (arXiv)

LLM watermarking, which embeds imperceptible yet algorithmically detectable signals in model outputs to identify LLM-generated text, has become crucial in mitigating the potential misuse of large language models. However, the abundance of LLM watermarking algorithms, their intricate mechanisms, and the complex evaluation procedures and perspectives pose challenges for researchers and the community to easily experiment with, understand, and assess the latest advancements. To address these issues, we introduce MarkLLM, an open-source toolkit for LLM watermarking. MarkLLM offers a unified and extensible framework for implementing LLM watermarking algorithms, while providing user-friendly interfaces to ensure ease of access. Furthermore, it enhances understanding by supporting automatic visualization of the underlying mechanisms of these algorithms. For evaluation, MarkLLM offers a comprehensive suite of 12 tools spanning three perspectives, along with two types of automated evaluation pipelines. Through MarkLLM, we aim to support researchers while improving the comprehension and involvement of the general public in LLM watermarking technology, fostering consensus and driving further advancements in research and application. Our code is available at https://github.com/THU-BPM/MarkLLM.

Key facts. Cited by 80 papers in the map (data through 7 Oct 2026). Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security. Builds on 23 of its 39 references that are in the map. First posted on arXiv 16 May 2024.

Builds on

23 of 39 references.

Closest ancestors · 12

Same direction, newest first

  1. 2024An Entropy-based Text Watermarking Detection Method20 Mar
  2. 2023A Survey of Text Watermarking in the Era of Large Language Models13 Dec
  3. 2023On the Learnability of Watermarks for Language Models7 Dec
  4. 2023Mark My Words: Analyzing and Evaluating Language Model Watermarks1 Dec
  5. 2023A Robust Semantics-based Watermark for Large Language Model against Paraphrasing15 Nov
  6. 2023Publicly-Detectable Watermarking for Language Models27 Oct
  7. 2023Towards Codable Watermarking for Injecting Multi-bits Information to LLMs29 Jul
  8. 2023Robust Distortion-free Watermarks for Language Models28 Jul
  9. 2023Provable Robust Watermarking for AI-Generated Text30 Jun
  10. 2023Who Wrote this Code? Watermarking for Code Generation24 May
  11. 2023Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense23 Mar
  12. 2023A Watermark for Large Language Models24 Jan

Other references · 11

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  5. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  6. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,290
  7. 2023StarCoder: may the source be with you!cited by 790
  8. 2023Large Language Models for Information Retrieval: A Surveycited by 331
  9. 2023In-Context Impersonation Reveals Large Language Models' Strengths and Biasescited by 154
  10. 2023A Confederacy of Models: a Comprehensive Evaluation of LLMs on Creative Writingcited by 98
  11. 2023HowkGPT: Investigating the Detection of ChatGPT-generated University Student Homework through Context-Aware Perplexity Analysiscited by 30

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 41; 2026: 32.

80 papers.

Sort:

By area:

  1. 2024SoK: Watermarking for AI-Generated Contentcited by 43
  2. 2025Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Surveycited by 29
  3. 2025Frontier AI's Impact on the Cybersecurity Landscapecited by 21
  4. 2024Watermarking Techniques for Large Language Models: A Surveycited by 20
  5. 2026Large Language Model Reasoning Failurescited by 20
  6. 2025CoheMark: A Novel Sentence-Level Watermark for Enhanced Text Qualitycited by 17
  7. 2025Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation?cited by 16
  8. 2025Mark Your LLM: Detecting the Misuse of Open-Source Large Language Models via Watermarkingcited by 14
  9. 2025PMark: Towards Robust and Distortion-free Semantic-level Watermarking with Channel Constraintscited by 14
  10. 2025SimMark: A Robust Sentence-Level Similarity-Based Watermarking Algorithm for Large Language Modelscited by 13
  11. 2025Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attackscited by 12
  12. 2024Optimizing Adaptive Attacks against Watermarks for Language Modelscited by 11
38 more
  1. 2025Dataset Protection via Watermarked Canaries in Retrieval-Augmented LLMscited by 11
  2. 2024Can Watermarked LLMs be Identified by Users via Crafted Prompts?cited by 10
  3. 2024WaterSeeker: Pioneering Efficient Detection of Watermarked Segments in Large Documentscited by 9
  4. 2025Unified attacks to large language model watermarks: spoofing and scrubbing in unauthorized knowledge distillationcited by 9
  5. 2025Optimized Couplings for Watermarking Large Language Modelscited by 9
  6. 2025In-Context Watermarks for Large Language Modelscited by 9
  7. 2025Watermarking Diffusion Language Modelscited by 9
  8. 2025Agent Guide: A Simple Agent Behavioral Watermarking Frameworkcited by 8
  9. 2025Character-Level Perturbations Disrupt LLM Watermarkscited by 7
  10. 2025Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoptioncited by 7
  11. 2025From Trade-off to Synergy: A Versatile Symbiotic Watermarking Framework for Large Language Modelscited by 5
  12. 2025Invisible Entropy: Towards Safe and Efficient Low-Entropy LLM Watermarkingcited by 5
  13. 2025SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoderscited by 5
  14. 2025MarkDiffusion: An Open-Source Toolkit for Generative Watermarking of Latent Diffusion Modelscited by 5
  15. 2025Robustness Assessment and Enhancement of Text Watermarking for Google's SynthIDcited by 4
  16. 2025Factuality Beyond Coherence: Evaluating LLM Watermarking Methods for Medical Textscited by 4
  17. 2025DMark: Order-Agnostic Watermarking for Diffusion Large Language Modelscited by 4
  18. 2026LR-DWM: Efficient Watermarking for Diffusion Language Modelscited by 4
  19. 2024CredID: Credible Multi-Bit Watermark for Large Language Models Identificationcited by 3
  20. 2025BiMarker: Enhancing Text Watermark Detection for Large Language Models with Bipolar Watermarkscited by 3
  21. 2025The Feasibility of Topic-Based Watermarking on Academic Peer Reviewscited by 3
  22. 2025Majority Bit-Aware Watermarking For Large Language Modelscited by 3
  23. 2026Distilling the Thought, Watermarking the Answer: A Principle Semantic Guided Watermark for Large Reasoning Modelscited by 3
  24. 2026A Visual Semantic Adaptive Watermark grounded by Prefix-Tuning for Large Vision-Language Modelcited by 3
  25. 2025Sandcastles in the Storm: Revisiting the (Im)possibility of Strong Watermarkingcited by 2
  26. 2025SoK: Are Watermarks in LLMs Ready for Deployment?cited by 2
  27. 2025A Linguistics-Aware LLM Watermarking via Syntactic Predictabilitycited by 2
  28. 2025How Good is Post-Hoc Watermarking With Language Model Rephrasing?cited by 2
  29. 2026When Only the Final Text Survives: Implicit Execution Tracing for Multi-Agent Auditingcited by 2
  30. 2026TextSeal: A Localized LLM Watermark for Provenance & Distillation Protectioncited by 2
  31. 2026Watermarking Should Be Treated as a Monitoring Primitivecited by 2
  32. 2025Cross-Lingual Summarization as a Black-Box Watermark Removal Attackcited by 1
  33. 2026Decoder Gradient Shields: A Family of Provable and High-Fidelity Methods Against Gradient-Based Box-Free Watermark Removalcited by 1
  34. 2026AGMark: Attention-Guided Dynamic Watermarking for Large Vision-Language Modelscited by 1
  35. 2026Block-wise Codeword Embedding for Reliable Multi-bit Text Watermarkingcited by 1
  36. 2026SLAM: Structural Linguistic Activation Marking for Language Modelscited by 1
  37. 2026Every Bit, Everywhere, All at Once: A Binomial Multibit LLM Watermarkcited by 1
  38. 2026Robust LLM Watermarking with Minimal Semantic Distortion for IP Protectioncited by 1

50 most cited of 80 All 80 (JSON)