THU-BPM/MarkLLM
MarkLLM: An Open-Source Toolkit for LLM Watermarking.（EMNLP 2024 System Demonstration)
Provides modular implementations of multiple watermarking algorithms (including KGW, SemStamp, IE, MorphMark, and others) with unified interfaces for embedding, detection, and evaluation across different LLM architectures. The toolkit abstracts watermarking as configurable pipelines supporting both statistical detection methods and semantic-aware approaches, integrating with Hugging Face models and offering visualization tools for mechanism analysis.
829 stars and 133 monthly downloads. Actively maintained with 6 commits in the last 30 days. Available on PyPI.
Stars
829
Forks
82
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 09, 2026
Monthly downloads
133
Commits (30d)
6
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