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

arXiv: https://arxiv.org/abs/2606.24163 · HTML: https://mlsanity.com/paper/2606.24163/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security.
- Builds on 19 of its 32 references that are in the map.
- First posted on arXiv 23 Jun 2026.

## Placed in

- LLM safety and security / [Watermarking generated content and models](https://mlsanity.com/safety/watermarking-generated-content-and-models/)

## Builds on (most cited first, 19 of 19)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense](https://mlsanity.com/paper/2303.13408/) (2023)
- [Provable Robust Watermarking for AI-Generated Text](https://mlsanity.com/paper/2306.17439/) (2023)
- [MarkLLM: An Open-Source Toolkit for LLM Watermarking](https://mlsanity.com/paper/2405.10051/) (2024)
- [Advancing Beyond Identification: Multi-bit Watermark for Large Language Models](https://mlsanity.com/paper/2308.00221/) (2023)
- [A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models](https://mlsanity.com/paper/2310.07710/) (2023)
- [Provably Robust Multi-bit Watermarking for AI-generated Text](https://mlsanity.com/paper/2401.16820/) (2024)
- [Pseudorandom Error-Correcting Codes](https://mlsanity.com/paper/2402.09370/) (2024)
- [Attacking Neural Text Detectors](https://mlsanity.com/paper/2002.11768/) (2020)
- [Necessary and Sufficient Watermark for Large Language Models](https://mlsanity.com/paper/2310.00833/) (2023)
- [Watermarking Language Models with Error Correcting Codes](https://mlsanity.com/paper/2406.10281/) (2024)
- [Block-wise Codeword Embedding for Reliable Multi-bit Text Watermarking](https://mlsanity.com/paper/2605.00348/) (2026)

## Abstract (arXiv)

Reliable provenance for LLM outputs requires multi-bit watermarks that remain robust under editing while maintaining low false-positive rates. Existing ECC-based LLM watermarks rely on hard-decision decoding, discarding token-level reliability information and limiting robustness under post-generation edits. We propose CORE-BREW, a COnstant-hit-Rate Embedding extension of BREW for multi-bit watermarking. CORE-BREW calibrates the watermark channel by targeting a fixed hit rate p^star, yielding closed-form per-token log-likelihood ratios (LLRs) for soft-decision decoding. It incorporates entropy-aware erasures to limit perturbations in low-entropy contexts and combines likelihood-based scoring with soft-decision list decoding to exploit soft evidence. Experiments on open-source LLMs under token-level edits and paraphrasing demonstrate that CORE-BREW generally improves detection robustness and payload recovery over the BREW baseline while maintaining low observed false-positive rates. Despite higher conditional perplexity, BLEU and BERTScore remain close to those of unwatermarked text, indicating comparable reference-based translation quality.