arXiv Computation and Language September 30, 2026 By Joeun Kim, HoEun Kim, Young-Sik Kim

CORE-BREW: LLR-Based Soft Decoding for Robust Multi-Bit LLM Watermarking

Read the original on arXiv Computation and Language →

CORE-BREW is a new multi‑bit watermarking method for large language models that uses log‑likelihood ratios for soft‑decision decoding, targeting a fixed hit rate to calibrate the watermark channel. It introduces entropy‑aware erasures to reduce perturbations in low‑entropy contexts and combines likelihood‑based scoring with soft‑decision list decoding to better exploit token‑level reliability. Experiments on open‑source LLMs show that CORE‑BREW improves detection robustness and payload recovery compared to the BREW baseline while keeping false‑positive rates low and maintaining translation quality metrics close to unwatermarked text.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Hugging Face Trending Papers

Jun 23

CORE-BREW: LLR-Based Soft Decoding for Robust Multi-Bit LLM Watermarking

Reliable provenance for LLM outputs requires multi-bit watermarks that remain robust under editing while maintaining strict false-positive control. Existing ECC-based LLM watermarks rely largely on hard-decision decoding, discarding token-level reliability information.

llms rag

arXiv Computation and Language

1d ago

Anchor-ECC: Local Integrity Checking for Watermarked LLM Outputs via Error-Correcting Codes

arXiv:2609.38722v1 Announce Type: cross Abstract: LLM watermarking has become an effective approach to distinguishing AI-generated text from human-written text by embedding detectable patterns during...

By Zewei Deng, Muhammad Siddeek, Liyan Xie, Mohamed Seif, Mengdi Wang, H. Vincent Poor, Andrea Goldsmith

llms rag

arXiv Machine Learning

Jun 18

Signature filtering: a lightweight enhancement for statistical watermark detection in large language models

arXiv:2606. 18430v1 Announce Type: new Abstract: Statistical watermarks help organizations attribute large language model (LLM) outputs, yet existing detectors often struggle when watermark signals are weak, texts are repetitive, or watermarks are edited.

By Chih-Duo Hong, Yen-Pang Chen, Fang Yu

llms rag benchmarks

arXiv Machine Learning

Aug 17

Semantic Differentiation for Tackling Challenges in Watermarking Low-Entropy Constrained Generation Outputs

arXiv:2601. 11629v2 Announce Type: replace-cross Abstract: We demonstrate that while the current approaches for language model watermarking are effective for open-ended generation, they are inadequate at watermarking LM outputs for constrained generation tasks with low-entropy output spaces.

By Nghia T. Le, Alan Ritter, Kartik Goyal

llms nlp

arXiv Machine Learning

Sep 3

WeaveMark: Robust and Scalable Multi-bit LLM Watermarking via Coded Payload Spreading

WeaveMark is a new multi‑bit watermarking scheme for large language models that improves payload capacity, extraction accuracy, and text quality by using coded payload spreading, soft‑decision error‑correcting codes, and unbiased multilayer reweighting. It also adds zero‑bit layers for reliable detection of watermark presence. Experiments demonstrate significant gains, achieving an 89.8% match rate for 32‑bit messages at 200 tokens and maintaining 86.0% accuracy under 10% substitution attacks on 16‑bit messages, far outperforming the BiMark baseline.

By Gang-Hyun Park, Ju-Hyeong Lee, Hee-Youl Kwak, Dae-Young Yun

llms rag

arXiv AI

Aug 14

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks

arXiv:2608. 12713v1 Announce Type: cross Abstract: Watermarking LLM-generated text is an important task for tracing its provenance.

By Xiaoyan Feng, Yanjun Zhang, He Zhang, Leo Yu Zhang, Shirui Pan

llms rag benchmarks

One email a morning, machine-written

Related stories

CORE-BREW: LLR-Based Soft Decoding for Robust Multi-Bit LLM Watermarking

Anchor-ECC: Local Integrity Checking for Watermarked LLM Outputs via Error-Correcting Codes

Signature filtering: a lightweight enhancement for statistical watermark detection in large language models

Semantic Differentiation for Tackling Challenges in Watermarking Low-Entropy Constrained Generation Outputs

WeaveMark: Robust and Scalable Multi-bit LLM Watermarking via Coded Payload Spreading

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks