mlsanityData to 7 Oct 2026

Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy

arXiv 2307.13808 ↗First posted 25 Jul 2023cs.CL cs.CRcited by 45

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

Abstract (arXiv)

To mitigate potential risks associated with language models, recent AI detection research proposes incorporating watermarks into machine-generated text through random vocabulary restrictions and utilizing this information for detection. While these watermarks only induce a slight deterioration in perplexity, our empirical investigation reveals a significant detriment to the performance of conditional text generation. To address this issue, we introduce a simple yet effective semantic-aware watermarking algorithm that considers the characteristics of conditional text generation and the input context. Experimental results demonstrate that our proposed method yields substantial improvements across various text generation models, including BART and Flan-T5, in tasks such as summarization and data-to-text generation while maintaining detection ability.

Key facts. Cited by 45 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 26 of its 48 references that are in the map. First posted on arXiv 25 Jul 2023.

Builds on

26 of 48 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023Who Wrote this Code? Watermarking for Code Generation24 May
  2. 2023Watermarking Text Generated by Black-Box Language Models14 May
  3. 2023Can AI-Generated Text be Reliably Detected?17 Mar
  4. 2023Protecting Language Generation Models via Invisible Watermarking6 Feb

Other references · 22

  1. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  3. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,332
  4. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,308
  5. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
  6. 2023DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvaturecited by 705
  7. 2019Release Strategies and the Social Impacts of Language Modelscited by 505
  8. 2023Toxicity in ChatGPT: Analyzing Persona-assigned Language Modelscited by 356
  9. 2022News Summarization and Evaluation in the Era of GPT-3cited by 324
  10. 2023Self-collaboration Code Generation via ChatGPTcited by 255
  11. 2020Automatic Detection of Machine Generated Text: A Critical Surveycited by 160
  12. 2019Challenges in Building Intelligent Open-domain Dialog Systemscited by 147
10 more
  1. 2020DART: Open-Domain Structured Data Record to Text Generationcited by 144
  2. 2023Self-Edit: Fault-Aware Code Editor for Code Generationcited by 110
  3. 2019Neural Machine Translation: A Review and Surveycited by 99
  4. 2019Real or Fake? Learning to Discriminate Machine from Human Generated Textcited by 98
  5. 2023ChatGPT or Human? Detect and Explain. Explaining Decisions of Machine Learning Model for Detecting Short ChatGPT-generated Textcited by 84
  6. 2019The Limitations of Stylometry for Detecting Machine-Generated Fake Newscited by 63
  7. 2023ChatGPT is a Knowledgeable but Inexperienced Solver: An Investigation of Commonsense Problem in Large Language Modelscited by 63
  8. 2021Sequence Level Contrastive Learning for Text Summarizationcited by 31
  9. 2020CDEvalSumm: An Empirical Study of Cross-Dataset Evaluation for Neural Summarization Systemscited by 17
  10. 2022What Makes Data-to-Text Generation Hard for Pretrained Language Models?cited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 12; 2025: 17; 2026: 8.

45 papers.

Sort:

By area:

  1. 2024Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviewscited by 160
  2. 2023A Survey of Text Watermarking in the Era of Large Language Modelscited by 102
  3. 2023On the Learnability of Watermarks for Language Modelscited by 72
  4. 2023A Survey on Detection of LLMs-Generated Contentcited by 70
  5. 2024Watermarking Makes Language Models Radioactivecited by 52
  6. 2024k-SemStamp: A Clustering-Based Semantic Watermark for Detection of Machine-Generated Textcited by 46
  7. 2024Copyright Protection in Generative AI: A Technical Perspectivecited by 35
  8. 2023WaterBench: Towards Holistic Evaluation of Watermarks for Large Language Modelscited by 27
  9. 2023Towards Optimal Statistical Watermarkingcited by 25
  10. 2024Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Surveycited by 23
  11. 2023Optimizing watermarks for large language modelscited by 22
  12. 2024Watermarking Techniques for Large Language Models: A Surveycited by 20
33 more
  1. 2025SimMark: A Robust Sentence-Level Similarity-Based Watermarking Algorithm for Large Language Modelscited by 13
  2. 2023Watermarking Vision-Language Pre-trained Models for Multi-modal Embedding as a Servicecited by 11
  3. 2025Defending LLM Watermarking Against Spoofing Attacks with Contrastive Representation Learningcited by 10
  4. 2024WaterJudge: Quality-Detection Trade-off when Watermarking Large Language Modelscited by 9
  5. 2024AI-Generated Text Detection and Classification Based on BERT Deep Learning Algorithmcited by 8
  6. 2025Marking Code Without Breaking It: Code Watermarking for Detecting LLM-Generated Codecited by 7
  7. 2023Improving the Generation Quality of Watermarked Large Language Models via Word Importance Scoringcited by 6
  8. 2025Detecting Benchmark Contamination Through Watermarkingcited by 6
  9. 2025From Trade-off to Synergy: A Versatile Symbiotic Watermarking Framework for Large Language Modelscited by 5
  10. 2025Invisible Entropy: Towards Safe and Efficient Low-Entropy LLM Watermarkingcited by 5
  11. 2025Paladin: Defending LLM-enabled Phishing Emails with a New Trigger-Tag Paradigmcited by 4
  12. 2025WaterMod: Modular Token-Rank Partitioning for Probability-Balanced LLM Watermarkingcited by 4
  13. 2026PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attackscited by 4
  14. 2024From Intentions to Techniques: A Comprehensive Taxonomy and Challenges in Text Watermarking for Large Language Modelscited by 3
  15. 2024"Sora is Incredible and Scary": Emerging Governance Challenges of Text-to-Video Generative AI Modelscited by 3
  16. 2025Watermarking Degrades Alignment in Language Models: Analysis and Mitigationcited by 3
  17. 2024Decoding at the Speed of Thought: Harnessing Parallel Decoding of Lexical Units for LLMscited by 2
  18. 2025SoK: Are Watermarks in LLMs Ready for Deployment?cited by 2
  19. 2025How Good is Post-Hoc Watermarking With Language Model Rephrasing?cited by 2
  20. 2026TextSeal: A Localized LLM Watermark for Provenance & Distillation Protectioncited by 2
  21. 2024Discourse Features Enhance Detection of Document-Level Machine-Generated Contentcited by 1
  22. 2025Spread them Apart: Towards Robust Watermarking of Generated Contentcited by 1
  23. 2025Learning to Watermark: A Selective Watermarking Framework for Large Language Models via Multi-Objective Optimizationcited by 1
  24. 2025Is Multilingual LLM Watermarking Truly Multilingual? Scaling Robustness to 100+ Languages via Back-Translationcited by 1
  25. 2026DSIPA: Detecting LLM-Generated Texts via Sentiment-Invariant Patterns Divergence Analysiscited by 1
  26. 2026SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase Robustnesscited by 1
  27. 2025DERMARK: A Dynamic, Efficient and Robust Multi-bit Watermark for Large Language Modelscited by 0
  28. 2025Toward Copyright Integrity and Verifiability via Multi-Bit Watermarking for Intelligent Transportation Systemscited by 0
  29. 2025CEFW: A Comprehensive Evaluation Framework for Watermark in Large Language Modelscited by 0
  30. 2026BanglaLorica: Design and Evaluation of a Robust Watermarking Algorithm for Large Language Models in Bangla Text Generationcited by 0
  31. 2026Beyond A Fixed Seal: Adaptive Stealing Watermark in Large Language Modelscited by 0
  32. 2026LLM Output Detectability and Task Performance Can be Jointly Optimizedcited by 0
  33. 2026AliMark: Enhancing Robustness of Sentence-Level Watermarking Against Text Paraphrasingcited by 0