Pith. sign in

REVIEW 5 cited by

MarkLLM: An Open-Source Toolkit for LLM Watermarking

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2405.10051 v6 pith:5C3LV5NS submitted 2024-05-16 cs.CR cs.CL

Leyi Pan , Aiwei Liu , Zhiwei He , Zitian Gao , Xuandong Zhao , Yijian Lu , Binglin Zhou , Shuliang Liu
show 4 more authors
Xuming Hu Lijie Wen Irwin King Philip S. Yu
This is my paper
classification cs.CRcs.CL
keywords markllmwatermarkingalgorithmsevaluationadvancementsmechanismsoffersopen-source
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

LLM watermarking, which embeds imperceptible yet algorithmically detectable signals in model outputs to identify LLM-generated text, has become crucial in mitigating the potential misuse of large language models. However, the abundance of LLM watermarking algorithms, their intricate mechanisms, and the complex evaluation procedures and perspectives pose challenges for researchers and the community to easily experiment with, understand, and assess the latest advancements. To address these issues, we introduce MarkLLM, an open-source toolkit for LLM watermarking. MarkLLM offers a unified and extensible framework for implementing LLM watermarking algorithms, while providing user-friendly interfaces to ensure ease of access. Furthermore, it enhances understanding by supporting automatic visualization of the underlying mechanisms of these algorithms. For evaluation, MarkLLM offers a comprehensive suite of 12 tools spanning three perspectives, along with two types of automated evaluation pipelines. Through MarkLLM, we aim to support researchers while improving the comprehension and involvement of the general public in LLM watermarking technology, fostering consensus and driving further advancements in research and application. Our code is available at https://github.com/THU-BPM/MarkLLM.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Cryptanalysis of LDPC-Based Pseudorandom Error-Correcting Codes

    cs.CR 2025-12 conditional novelty 7.0 of 10

    Watermarks based on LDPC pseudorandom error-correcting codes can be detected with about 2^22 operations, and robustness can be undermined by a noise-overlay attack, across practical parameter ranges.

  2. SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase Robustness

    cs.CR 2026-05 unverdicted novelty 6.5 of 10

    SAMark uses self-anchored semantic green regions, multi-channel hyperbolic scoring, and diversity-aware filtering to reach 90.2% TP@FP1% detection under paragraph paraphrasing while preserving text quality.

  3. LLM Watermark Evasion via Bias Inversion

    cs.CR 2025-09 conditional novelty 6.0 of 10

    Applying a negative logit bias to high-surprisal tokens during LLM paraphrasing drops the green-token rate below the detector threshold, driving watermark detection probability down exponentially and yielding over 99%...

  4. Enhancing Watermarking Quality for LLMs via Contextual Generation States Awareness

    cs.CR 2025-06 conditional novelty 6.0 of 10

    A context-aware plug-in for LLM watermarking that skips or weakens watermarks on semantically critical tokens, improving task accuracy at similar detection rates.

  5. MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection

    cs.CR 2025-05 conditional novelty 6.0 of 10

    MUSE embeds a watermark in tabular synthetic data by selecting, among several generated candidate rows, the one with the highest keyed hash score, enabling detection without model inversion.

Pith tools