The paper investigates watermarking for large language model outputs, noting that stronger single-layer watermarks reduce token entropy and weaken subsequent layers. It demonstrates that detectability is limited by entropy and that watermark ensembles monotonically lower entropy and the green‑list ratio. The authors propose using weaker single‑layer watermarks to maintain entropy, showing through theory and experiments that this approach improves both detectability and robustness compared to strong baselines.
arXiv:2602. 09611v2 Announce Type: replace-cross Abstract: Watermarking has emerged as a pivotal solution for content traceability and intellectual property protection in large vision language models (LVLMs).
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:2608.27899v1 Announce Type: cross Abstract: With the growing prevalence of large language model (LLM) generated content, watermarking is considered a promising approach for attributing text to...
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:2607. 13099v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved remarkable success but raise growing concerns about content provenance and misuse, motivating the need for reliable watermarking techniques.
arXiv:2607. 20435v1 Announce Type: cross Abstract: Open-source LLMs (OSMs)arereaching near state-of-the-art performance, prompting prior works to trace the text they generate by embedding text watermarking algorithms directly into their weights.
arXiv:2608. 06416v1 Announce Type: cross Abstract: Watermarking traces the provenance of text produced by large language models by embedding statistically detectable signals during decoding.
arXiv:2606. 00613v1 Announce Type: cross Abstract: Watermarking should identify language-model output without degrading quality or limiting verification to the model provider.
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.
arXiv:2609.02177v1 Announce Type: cross Abstract: Multi-bit watermarking for large language models (LLMs) enables content source tracing by embedding user-identifiable messages into generated text. E...
arXiv:2608. 12713v1 Announce Type: cross Abstract: Watermarking LLM-generated text is an important task for tracing its provenance.
The paper introduces an adaptive embedding displacement attack (EDA) that exploits rewording, reordering, and resegmentation to remove semantic watermarks from text, achieving a 32.6%–47.9% success rate across four watermarking schemes. To counter this, the authors propose k‑SwordStamp, a semantic watermarking method that uses order‑robust detection over sub‑sentence units, significantly reducing vulnerability to structure‑based edits. Experiments show that EDA remains effective against k‑SwordStamp, but with a lower success rate (10.8%) compared to its performance on other schemes.