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

arXiv: https://arxiv.org/abs/2307.13808 · HTML: https://mlsanity.com/paper/2307.13808/

## Key facts

- Cited by 50 papers in the map (data through 14 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.

## Placed in

- LLM safety and security / [Watermarking generated content and models](https://mlsanity.com/safety/watermarking-generated-content-and-models/)

## Builds on (most cited first, 26 of 26)

- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [Release Strategies and the Social Impacts of Language Models](https://mlsanity.com/paper/1908.09203/) (2019)
- [Can AI-Generated Text be Reliably Detected?](https://mlsanity.com/paper/2303.11156/) (2023)
- [Toxicity in ChatGPT: Analyzing Persona-assigned Language Models](https://mlsanity.com/paper/2304.05335/) (2023)
- [News Summarization and Evaluation in the Era of GPT-3](https://mlsanity.com/paper/2209.12356/) (2022)
- [Self-collaboration Code Generation via ChatGPT](https://mlsanity.com/paper/2304.07590/) (2023)
- [Automatic Detection of Machine Generated Text: A Critical Survey](https://mlsanity.com/paper/2011.01314/) (2020)
- [Challenges in Building Intelligent Open-domain Dialog Systems](https://mlsanity.com/paper/1905.05709/) (2019)
- [DART: Open-Domain Structured Data Record to Text Generation](https://mlsanity.com/paper/2007.02871/) (2020)
- [Who Wrote this Code? Watermarking for Code Generation](https://mlsanity.com/paper/2305.15060/) (2023)
- [Self-Edit: Fault-Aware Code Editor for Code Generation](https://mlsanity.com/paper/2305.04087/) (2023)
- [Neural Machine Translation: A Review and Survey](https://mlsanity.com/paper/1912.02047/) (2019)
- [Real or Fake? Learning to Discriminate Machine from Human Generated Text](https://mlsanity.com/paper/1906.03351/) (2019)
- [Protecting Language Generation Models via Invisible Watermarking](https://mlsanity.com/paper/2302.03162/) (2023)
- [ChatGPT or Human? Detect and Explain. Explaining Decisions of Machine Learning Model for Detecting Short ChatGPT-generated Text](https://mlsanity.com/paper/2301.13852/) (2023)
- [Watermarking Text Generated by Black-Box Language Models](https://mlsanity.com/paper/2305.08883/) (2023)
- [The Limitations of Stylometry for Detecting Machine-Generated Fake News](https://mlsanity.com/paper/1908.09805/) (2019)
- [ChatGPT is a Knowledgeable but Inexperienced Solver: An Investigation of Commonsense Problem in Large Language Models](https://mlsanity.com/paper/2303.16421/) (2023)
- [Sequence Level Contrastive Learning for Text Summarization](https://mlsanity.com/paper/2109.03481/) (2021)
- [CDEvalSumm: An Empirical Study of Cross-Dataset Evaluation for Neural Summarization Systems](https://mlsanity.com/paper/2010.05139/) (2020)
- [What Makes Data-to-Text Generation Hard for Pretrained Language Models?](https://mlsanity.com/paper/2205.11505/) (2022)

## Built on by (most cited first, 30 of 50)

- [Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews](https://mlsanity.com/paper/2403.07183/) (2024)
- [A Survey of Text Watermarking in the Era of Large Language Models](https://mlsanity.com/paper/2312.07913/) (2023)
- [On the Learnability of Watermarks for Language Models](https://mlsanity.com/paper/2312.04469/) (2023)
- [A Survey on Detection of LLMs-Generated Content](https://mlsanity.com/paper/2310.15654/) (2023)
- [Watermarking Makes Language Models Radioactive](https://mlsanity.com/paper/2402.14904/) (2024)
- [k-SemStamp: A Clustering-Based Semantic Watermark for Detection of Machine-Generated Text](https://mlsanity.com/paper/2402.11399/) (2024)
- [Copyright Protection in Generative AI: A Technical Perspective](https://mlsanity.com/paper/2402.02333/) (2024)
- [WaterBench: Towards Holistic Evaluation of Watermarks for Large Language Models](https://mlsanity.com/paper/2311.07138/) (2023)
- [Towards Optimal Statistical Watermarking](https://mlsanity.com/paper/2312.07930/) (2023)
- [Optimizing watermarks for large language models](https://mlsanity.com/paper/2312.17295/) (2023)
- [Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey](https://mlsanity.com/paper/2406.05392/) (2024)
- [Watermarking Techniques for Large Language Models: A Survey](https://mlsanity.com/paper/2409.00089/) (2024)
- [Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends](https://mlsanity.com/paper/2508.11548/) (2025)
- [SimMark: A Robust Sentence-Level Similarity-Based Watermarking Algorithm for Large Language Models](https://mlsanity.com/paper/2502.02787/) (2025)
- [Watermarking Vision-Language Pre-trained Models for Multi-modal Embedding as a Service](https://mlsanity.com/paper/2311.05863/) (2023)
- [Marking Code Without Breaking It: Code Watermarking for Detecting LLM-Generated Code](https://mlsanity.com/paper/2502.18851/) (2025)
- [Defending LLM Watermarking Against Spoofing Attacks with Contrastive Representation Learning](https://mlsanity.com/paper/2504.06575/) (2025)
- [WaterJudge: Quality-Detection Trade-off when Watermarking Large Language Models](https://mlsanity.com/paper/2403.19548/) (2024)
- [AI-Generated Text Detection and Classification Based on BERT Deep Learning Algorithm](https://mlsanity.com/paper/2405.16422/) (2024)
- [PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks](https://mlsanity.com/paper/2605.10977/) (2026)
- [Improving the Generation Quality of Watermarked Large Language Models via Word Importance Scoring](https://mlsanity.com/paper/2311.09668/) (2023)
- [Detecting Benchmark Contamination Through Watermarking](https://mlsanity.com/paper/2502.17259/) (2025)
- [Invisible Entropy: Towards Safe and Efficient Low-Entropy LLM Watermarking](https://mlsanity.com/paper/2505.14112/) (2025)
- [WaterMod: Modular Token-Rank Partitioning for Probability-Balanced LLM Watermarking](https://mlsanity.com/paper/2511.07863/) (2025)
- [From Trade-off to Synergy: A Versatile Symbiotic Watermarking Framework for Large Language Models](https://mlsanity.com/paper/2505.09924/) (2025)
- [Paladin: Defending LLM-enabled Phishing Emails with a New Trigger-Tag Paradigm](https://mlsanity.com/paper/2509.07287/) (2025)
- [A Reinforcement Learning Framework for Robust and Secure LLM Watermarking](https://mlsanity.com/paper/2510.21053/) (2025)
- [TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection](https://mlsanity.com/paper/2605.12456/) (2026)
- [Performance-lossless Black-box Model Watermarking](https://mlsanity.com/paper/2312.06488/) (2023)
- [From Intentions to Techniques: A Comprehensive Taxonomy and Challenges in Text Watermarking for Large Language Models](https://mlsanity.com/paper/2406.11106/) (2024)

## 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.