# The Ethical Need for Watermarks in Machine-Generated Language

arXiv: https://arxiv.org/abs/2209.03118 · HTML: https://mlsanity.com/paper/2209.03118/

## Key facts

- Cited by 32 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 10 of its 30 references that are in the map.
- First posted on arXiv 7 Sep 2022.

## 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, 10 of 10)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [Scaling Language Models: Methods, Analysis & Insights from Training Gopher](https://mlsanity.com/paper/2112.11446/) (2021)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Deal or No Deal? End-to-End Learning for Negotiation Dialogues](https://mlsanity.com/paper/1706.05125/) (2017)
- [DAWN: Dynamic Adversarial Watermarking of Neural Networks](https://mlsanity.com/paper/1906.00830/) (2019)
- [Protecting Intellectual Property of Language Generation APIs with Lexical Watermark](https://mlsanity.com/paper/2112.02701/) (2021)
- [Imitation Attacks and Defenses for Black-box Machine Translation Systems](https://mlsanity.com/paper/2004.15015/) (2020)
- [BloomNet: A Robust Transformer based model for Bloom's Learning Outcome Classification](https://mlsanity.com/paper/2108.07249/) (2021)

## Built on by (most cited first, 30 of 32)

- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense](https://mlsanity.com/paper/2303.13408/) (2023)
- [DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text](https://mlsanity.com/paper/2306.05540/) (2023)
- [On the Reliability of Watermarks for Large Language Models](https://mlsanity.com/paper/2306.04634/) (2023)
- [Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust](https://mlsanity.com/paper/2305.20030/) (2023)
- [Regulating ChatGPT and other Large Generative AI Models](https://mlsanity.com/paper/2302.02337/) (2023)
- [A Survey on Detection of LLMs-Generated Content](https://mlsanity.com/paper/2310.15654/) (2023)
- [On the Creativity of Large Language Models](https://mlsanity.com/paper/2304.00008/) (2023)
- [Leveraging Optimization for Adaptive Attacks on Image Watermarks](https://mlsanity.com/paper/2309.16952/) (2023)
- [SoK: Watermarking for AI-Generated Content](https://mlsanity.com/paper/2411.18479/) (2024)
- [Large Language Models can be Guided to Evade AI-Generated Text Detection](https://mlsanity.com/paper/2305.10847/) (2023)
- [Embarrassingly Simple Text Watermarks](https://mlsanity.com/paper/2310.08920/) (2023)
- [Mapping the Ethics of Generative AI: A Comprehensive Scoping Review](https://mlsanity.com/paper/2402.08323/) (2024)
- [Self-Recognition in Language Models](https://mlsanity.com/paper/2407.06946/) (2024)
- [Optimizing Adaptive Attacks against Watermarks for Language Models](https://mlsanity.com/paper/2410.02440/) (2024)
- [The Age of Synthetic Realities: Challenges and Opportunities](https://mlsanity.com/paper/2306.11503/) (2023)
- [RAFT: Realistic Attacks to Fool Text Detectors](https://mlsanity.com/paper/2410.03658/) (2024)
- [Dual Use Concerns of Generative AI and Large Language Models](https://mlsanity.com/paper/2305.07882/) (2023)
- [AI Regulation in Europe: From the AI Act to Future Regulatory Challenges](https://mlsanity.com/paper/2310.04072/) (2023)
- [Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systems](https://mlsanity.com/paper/2606.28425/) (2026)
- [SEFD: Semantic-Enhanced Framework for Detecting LLM-Generated Text](https://mlsanity.com/paper/2411.12764/) (2024)
- [BiMarker: Enhancing Text Watermark Detection for Large Language Models with Bipolar Watermarks](https://mlsanity.com/paper/2501.12174/) (2025)
- [Watermarking Degrades Alignment in Language Models: Analysis and Mitigation](https://mlsanity.com/paper/2506.04462/) (2025)
- [Enhancing Watermarking Quality for LLMs via Contextual Generation States Awareness](https://mlsanity.com/paper/2506.07403/) (2025)
- [On the Detectability of LLM-Generated Text: What Exactly Is LLM-Generated Text?](https://mlsanity.com/paper/2510.20810/) (2025)
- [Authorship and the Politics and Ethics of LLM Watermarks](https://mlsanity.com/paper/2403.06593/) (2024)
- [Ethics Whitepaper: Whitepaper on Ethical Research into Large Language Models](https://mlsanity.com/paper/2410.19812/) (2024)
- [We Need Improved Data Curation and Attribution in AI for Scientific Discovery](https://mlsanity.com/paper/2504.02486/) (2025)
- [Temperature Matters: Enhancing Watermark Robustness Against Paraphrasing Attacks](https://mlsanity.com/paper/2506.22623/) (2025)
- [Watermarking Large Language Models in Europe: Interpreting the AI Act in Light of Technology](https://mlsanity.com/paper/2511.03641/) (2025)

## Abstract (arXiv)

Watermarks should be introduced in the natural language outputs of AI systems in order to maintain the distinction between human and machine-generated text. The ethical imperative to not blur this distinction arises from the asemantic nature of large language models and from human projections of emotional and cognitive states on machines, possibly leading to manipulation, spreading falsehoods or emotional distress. Enforcing this distinction requires unintrusive, yet easily accessible marks of the machine origin. We propose to implement a code based on equidistant letter sequences. While no such code exists in human-written texts, its appearance in machine-generated ones would prove helpful for ethical reasons.