plll4zzx/Awesome-LLM-Watermark

A collection list for Large Language Model (LLM) Watermark

31
/ 100
Emerging

This collection helps researchers and practitioners explore various techniques for embedding hidden signals, or "watermarks," into text generated by large language models (LLMs). It compiles a wide range of academic papers, categorizing them by the specific method of watermarking (e.g., token-level, sentence-level) and related topics like watermark attacks and robustness. Anyone working on developing or deploying LLMs and concerned with content provenance, intellectual property, or detecting AI-generated text will find this resource valuable.

Use this if you need to understand the current landscape of LLM watermarking techniques, including how they work, their strengths, and their vulnerabilities.

Not ideal if you are looking for a ready-to-use software tool or a step-by-step guide to implement a specific watermark, as this is a research compilation.

AI-generated content LLM security text provenance AI ethics digital watermarking
No License No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 5 / 25

How are scores calculated?

Stars

58

Forks

2

Language

License

Last pushed

Feb 05, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/plll4zzx/Awesome-LLM-Watermark"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.