arXiv:2607. 00224v1 Announce Type: cross Abstract: Watermarking promises a statistical trace of large language model (LLM) use, but real documents, after editing or paraphrasing, rarely arrive as purely human-written or purely machine-generated.
arXiv:2506.22343v2 Announce Type: replace-cross Abstract: Text watermarks in large language models (LLMs) are an increasingly important tool for detecting synthetic text and distinguishing human-writ...
arXiv:2609.15657v1 Announce Type: cross Abstract: Keyed watermark detection tests dependence between observed tokens and pseudorandom variables reconstructed from a secret key. Building on the pivota...
arXiv:2608. 14906v1 Announce Type: cross Abstract: Watermarking provides a principled way to authenticate text generated by large language models (LLMs).
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.
The paper introduces the first watermark designed specifically for diffusion language models (DLMs), which generate tokens in arbitrary order unlike traditional autoregressive models. It overcomes the challenge of missing prior tokens by applying the watermark in expectation over the context and promoting tokens that strengthen the watermark when used as context. Experiments show a >99% true positive rate with minimal quality loss and comparable robustness to existing autoregressive watermarks.
arXiv:2509. 21160v2 Announce Type: replace-cross Abstract: With the growing use of large language models, concerns over content authenticity have spurred a variety of watermarking schemes.
arXiv:2607. 21958v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly deployed, reliable and efficient mechanisms for distinguishing AI-generated text from human-written content have become essential.
arXiv:2607. 05694v1 Announce Type: cross Abstract: Logit-based watermarking is a widely used mechanism for identifying LLM generated content, yet its effectiveness is governed by a fundamental trade-off between detectability and semantic distortion.
The paper investigates how watermarking affects recursive discrete distribution estimation when synthetic samples are mixed with real data. It establishes minimax lower bounds showing that, as the proportion of real samples approaches zero, adding watermarks cannot improve performance unless the false‑negative detection rate also vanishes. The authors further demonstrate that simple deterministic estimators achieve worst‑case losses close to these bounds and introduce a masking technique that reduces the remaining performance gap to a Jensen gap, suggesting potential for tighter bounds.
arXiv:2606. 00613v1 Announce Type: cross Abstract: Watermarking should identify language-model output without degrading quality or limiting verification to the model provider.
The paper introduces a new multi-draft speculative sampling algorithm that uses Poisson processes to improve inference efficiency and output provenance for large language models. It achieves strong sampling efficiency while allowing an unbiased watermark to be embedded without reducing speculative acceptance. The method relies on an exact list‑coupling‑without‑communication scheme, giving a drafter‑invariant property that benefits both sampling and watermarking, and the authors experimentally confirm its effectiveness.
arXiv:2607. 13003v1 Announce Type: cross Abstract: A watermark in a generative model's output is usually asked only whether a text is machine-made.