# Towards Codable Watermarking for Injecting Multi-bits Information to LLMs

arXiv: https://arxiv.org/abs/2307.15992 · HTML: https://mlsanity.com/paper/2307.15992/

## Key facts

- Cited by 54 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 24 of its 33 references that are in the map.
- First posted on arXiv 29 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, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [Release Strategies and the Social Impacts of Language Models](https://mlsanity.com/paper/1908.09203/) (2019)
- [Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense](https://mlsanity.com/paper/2303.13408/) (2023)
- [Can AI-Generated Text be Reliably Detected?](https://mlsanity.com/paper/2303.11156/) (2023)
- [Provable Robust Watermarking for AI-Generated Text](https://mlsanity.com/paper/2306.17439/) (2023)
- [On the Reliability of Watermarks for Large Language Models](https://mlsanity.com/paper/2306.04634/) (2023)
- [Automatic Detection of Machine Generated Text: A Critical Survey](https://mlsanity.com/paper/2011.01314/) (2020)
- [Who Wrote this Code? Watermarking for Code Generation](https://mlsanity.com/paper/2305.15060/) (2023)
- [Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding](https://mlsanity.com/paper/2009.03015/) (2020)
- [Real or Fake? Learning to Discriminate Machine from Human Generated Text](https://mlsanity.com/paper/1906.03351/) (2019)
- [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)
- [Three Bricks to Consolidate Watermarks for Large Language Models](https://mlsanity.com/paper/2308.00113/) (2023)
- [Robust Multi-bit Natural Language Watermarking through Invariant Features](https://mlsanity.com/paper/2305.01904/) (2023)
- [OUTFOX: LLM-Generated Essay Detection Through In-Context Learning with Adversarially Generated Examples](https://mlsanity.com/paper/2307.11729/) (2023)
- [Watermarking Text Generated by Black-Box Language Models](https://mlsanity.com/paper/2305.08883/) (2023)
- [Tracing Text Provenance via Context-Aware Lexical Substitution](https://mlsanity.com/paper/2112.07873/) (2021)
- [Is ChatGPT Involved in Texts? Measure the Polish Ratio to Detect ChatGPT-Generated Text](https://mlsanity.com/paper/2307.11380/) (2023)

## Built on by (most cited first, 30 of 54)

- [A Survey of Text Watermarking in the Era of Large Language Models](https://mlsanity.com/paper/2312.07913/) (2023)
- [MarkLLM: An Open-Source Toolkit for LLM Watermarking](https://mlsanity.com/paper/2405.10051/) (2024)
- [Large Language Model Safety: A Holistic Survey](https://mlsanity.com/paper/2412.17686/) (2024)
- [Provably Robust Multi-bit Watermarking for AI-generated Text](https://mlsanity.com/paper/2401.16820/) (2024)
- [CodeIP: A Grammar-Guided Multi-Bit Watermark for Large Language Models of Code](https://mlsanity.com/paper/2404.15639/) (2024)
- [BiMark: Unbiased Multilayer Watermarking for Large Language Models](https://mlsanity.com/paper/2506.21602/) (2025)
- [PMark: Towards Robust and Distortion-free Semantic-level Watermarking with Channel Constraints](https://mlsanity.com/paper/2509.21057/) (2025)
- [Downstream Trade-offs of a Family of Text Watermarks](https://mlsanity.com/paper/2311.09816/) (2023)
- [De-mark: Watermark Removal in Large Language Models](https://mlsanity.com/paper/2410.13808/) (2024)
- [WAPITI: A Watermark for Finetuned Open-Source LLMs](https://mlsanity.com/paper/2410.06467/) (2024)
- [StealthInk: A Multi-bit and Stealthy Watermark for Large Language Models](https://mlsanity.com/paper/2506.05502/) (2025)
- [WaterSeeker: Pioneering Efficient Detection of Watermarked Segments in Large Documents](https://mlsanity.com/paper/2409.05112/) (2024)
- [Enhancing LLM Watermark Resilience Against Both Scrubbing and Spoofing Attacks](https://mlsanity.com/paper/2507.06274/) (2025)
- [Watermarking Language Models through Language Models](https://mlsanity.com/paper/2411.05091/) (2024)
- [On Protecting Agentic Systems' Intellectual Property via Watermarking](https://mlsanity.com/paper/2602.08401/) (2026)
- [PersonaMark: Personalized LLM watermarking for model protection and user attribution](https://mlsanity.com/paper/2409.09739/) (2024)
- [SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders](https://mlsanity.com/paper/2508.08211/) (2025)
- [Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption](https://mlsanity.com/paper/2510.18333/) (2025)
- [Invisible Entropy: Towards Safe and Efficient Low-Entropy LLM Watermarking](https://mlsanity.com/paper/2505.14112/) (2025)
- [Building Intelligence Identification System via Large Language Model Watermarking: A Survey and Beyond](https://mlsanity.com/paper/2407.11100/) (2024)
- [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)
- [When AI Eats Itself: On the Caveats of AI Autophagy](https://mlsanity.com/paper/2405.09597/) (2024)
- [Robust and Minimally Invasive Watermarking for EaaS](https://mlsanity.com/paper/2410.17552/) (2024)
- [CredID: Credible Multi-Bit Watermark for Large Language Models Identification](https://mlsanity.com/paper/2412.03107/) (2024)
- [Majority Bit-Aware Watermarking For Large Language Models](https://mlsanity.com/paper/2508.03829/) (2025)
- [EditMark: Watermarking Large Language Models based on Model Editing](https://mlsanity.com/paper/2510.16367/) (2025)
- [Enhancing Watermarking Quality for LLMs via Contextual Generation States Awareness](https://mlsanity.com/paper/2506.07403/) (2025)
- [Multi-use LLM Watermarking and the False Detection Problem](https://mlsanity.com/paper/2506.15975/) (2025)
- [Distilling the Thought, Watermarking the Answer: A Principle Semantic Guided Watermark for Large Reasoning Models](https://mlsanity.com/paper/2601.05144/) (2026)

## Abstract (arXiv)

As large language models (LLMs) generate texts with increasing fluency and realism, there is a growing need to identify the source of texts to prevent the abuse of LLMs. Text watermarking techniques have proven reliable in distinguishing whether a text is generated by LLMs by injecting hidden patterns. However, we argue that existing LLM watermarking methods are encoding-inefficient and cannot flexibly meet the diverse information encoding needs (such as encoding model version, generation time, user id, etc.). In this work, we conduct the first systematic study on the topic of Codable Text Watermarking for LLMs (CTWL) that allows text watermarks to carry multi-bit customizable information. First of all, we study the taxonomy of LLM watermarking technologies and give a mathematical formulation for CTWL. Additionally, we provide a comprehensive evaluation system for CTWL: (1) watermarking success rate, (2) robustness against various corruptions, (3) coding rate of payload information, (4) encoding and decoding efficiency, (5) impacts on the quality of the generated text. To meet the requirements of these non-Pareto-improving metrics, we follow the most prominent vocabulary partition-based watermarking direction, and devise an advanced CTWL method named Balance-Marking. The core idea of our method is to use a proxy language model to split the vocabulary into probability-balanced parts, thereby effectively maintaining the quality of the watermarked text. Our code is available at https://github.com/lancopku/codable-watermarking-for-llm.