The Flow has not summarised this story yet — read it at 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.
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.
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.
arXiv:2608. 12713v1 Announce Type: cross Abstract: Watermarking LLM-generated text is an important task for tracing its provenance.
The paper introduces a dataset watermarking technique that embeds a watermark by increasing the co‑occurrence of randomly selected word pairs through meaning‑preserving local edits. The watermark can be detected solely from generated text with provable false‑positive control, and experiments on four base models and three datasets show reliable detection (p < 0.01) even when the watermarked data constitutes less than 5% of fine‑tuning tokens. Compared to existing methods, the approach better preserves benchmark utility and semantic integrity.
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.