THU-BPM/MarkLLM
MarkLLM: An Open-Source Toolkit for LLM Watermarking.（EMNLP 2024 System Demonstration)
This toolkit helps content creators, educators, and anyone generating text with Large Language Models (LLMs) to embed hidden signals into the output. You provide the LLM-generated text, and the tool returns the same text with an imperceptible 'watermark' that can later be detected to prove its origin. It's designed for users who need to verify if content was created by a specific AI model.
829 stars. Actively maintained with 3 commits in the last 30 days. Available on PyPI.
Use this if you need to reliably identify whether a piece of text was generated by a specific Large Language Model.
Not ideal if you are looking to watermark images or videos generated by AI, as this tool is specifically for text.
Stars
829
Forks
82
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 09, 2026
Commits (30d)
3
Dependencies
15
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/THU-BPM/MarkLLM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
git-disl/Vaccine
This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large...
zjunlp/Deco
[ICLR 2025] MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation
HillZhang1999/ICD
Code & Data for our Paper "Alleviating Hallucinations of Large Language Models through Induced...
voidism/DoLa
Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality...
kaist-cvml/I-HallA-v1.0
[AAAI 2025] Official Implementation of I-HallA v1.0