Every Bit, Everywhere, All at Once: A Binomial Multibit LLM Watermark

• URL: http://arxiv.org/abs/2605.11653v1
• Date: Tue, 12 May 2026 07:14:45 GMT
• Title: Every Bit, Everywhere, All at Once: A Binomial Multibit LLM Watermark
• Abstract summary: We introduce binomial encoding to encode every bit of the payload at every token position.<n>We complement our approach with a stateful encoder that dynamically redirects encoding pressure toward underencoded bits.<n>Our scheme achieves superior message accuracy and robustness, with the gap to baseline methods widening.
• Score: 16.543554028816477
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With LLM watermarking already being deployed commercially, practical applications increasingly require multibit watermarks that encode more complex payloads, such as user IDs or timestamps, into the generated text. In this work, we propose a fundamentally new approach for multibit watermarking: introducing binomial encoding to directly encode every bit of the payload at every token position. We complement our approach with a stateful encoder that during generation dynamically redirects encoding pressure toward underencoded bits. Our evaluation against 8 baselines on up to 64-bit payloads shows that our scheme achieves superior message accuracy and robustness, with the gap to baseline methods widening in more relevant settings (i.e., large payloads and low-distortion regimes). At the same time, we challenge prior works' evaluation metrics, highlighting their lack of practical insights, and introduce per-bit confidence scoring as a practically relevant metric for evaluating multibit LLM watermarks.

Related papers

• BitC-3DGS: High-Capacity 3D Gaussian Splatting Watermarking via Bit Compression [68.33622936663876]
  High-capacity watermarking is necessary for 3D Gaussian Splatting (3DGS) assets to embed rich information.<n>Existing bit-to-token watermarking methods are limited to 77-bit messages due to CLIP's fixed 77-token context length.<n>We introduce BitC-3DGS, a bit-compression framework that encodes multiple message bits per token.
  arXiv  Detail & Related papers  (2026-05-28T08:28:04Z)
• ArcMark: Multi-bit LLM Watermark via Optimal Transport [20.227686719113134]
  We present the first capacity characterization of multi-bit watermarks.<n>We show that ArcMark outperforms competing multi-bit watermarks in terms of bit rate per token and detection accuracy.
  arXiv  Detail & Related papers  (2026-02-06T22:28:03Z)
• From Bits to Rounds: Parallel Decoding with Exploration for Diffusion Language Models [19.97248408121574]
  Diffusion Language Models (DLMs) offer comparable accuracy with faster inference speed via parallel decoding.<n>High-confidence tokens carry negligible information and strictly relying on them limits the effective progress made in each decoding round.<n>We propose Explore-Then-Exploit (ETE), a training-free decoding strategy that maximizes information throughput and decoding efficiency.
  arXiv  Detail & Related papers  (2025-11-26T06:38:37Z)
• Majority Bit-Aware Watermarking For Large Language Models [7.200910949076064]
  MajorMark is a novel watermarking method that improves this trade-off through majority bit-aware encoding.<n>In contrast to prior methods that rely on token frequency analysis for decoding, MajorMark employs a clustering-based decoding strategy.<n>Extensive experiments on state-of-the-art LLMs demonstrate that our methods significantly enhance both decoding accuracy and text generation quality.
  arXiv  Detail & Related papers  (2025-08-05T18:19:00Z)
• METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models [92.37117312251755]
  We propose a progressive pruning framework, namely Multi-Encoder collaboraTivE tOken pRuning (METEOR)<n>For multi-vision encoding, we discard redundant tokens within each encoder via a rank guided collaborative token assignment strategy.<n>For multi-vision fusion, we combine the visual features from different encoders while reducing cross-encoder redundancy with cooperative pruning.
  arXiv  Detail & Related papers  (2025-07-28T13:50:53Z)
• Robust Multi-bit Text Watermark with LLM-based Paraphrasers [19.785484664254916]
  We propose an imperceptible multi-bit text watermark embedded by paraphrasing with LLMs.<n>To embed our watermark, we use two paraphrasers alternatively to encode the pre-defined binary code at the sentence level.<n>We show that our watermarks can achieve over 99.99% detection AUC with small (1.1B) text paraphrasers.
  arXiv  Detail & Related papers  (2024-12-04T08:43:12Z)
• Let the Code LLM Edit Itself When You Edit the Code [50.46536185784169]
  underlinetextbfPositional textbfIntegrity textbfEncoding (PIE)<n>PIE reduces computational overhead by over 85% compared to the standard full recomputation approach.<n>Results demonstrate that PIE reduces computational overhead by over 85% compared to the standard full recomputation approach.
  arXiv  Detail & Related papers  (2024-07-03T14:34:03Z)
• PostMark: A Robust Blackbox Watermark for Large Language Models [56.63560134428716]
  We develop PostMark, a modular post-hoc watermarking procedure. PostMark does not require logit access, which means it can be implemented by a third party. We show that PostMark is more robust to paraphrasing attacks than existing watermarking methods.
  arXiv  Detail & Related papers  (2024-06-20T17:27:14Z)
• CodeIP: A Grammar-Guided Multi-Bit Watermark for Large Language Models of Code [56.019447113206006]
  Large Language Models (LLMs) have achieved remarkable progress in code generation.<n>CodeIP is a novel multi-bit watermarking technique that inserts additional information to preserve provenance details.<n>Experiments conducted on a real-world dataset across five programming languages demonstrate the effectiveness of CodeIP.
  arXiv  Detail & Related papers  (2024-04-24T04:25:04Z)
• Parallel Decoding via Hidden Transfer for Lossless Large Language Model Acceleration [54.897493351694195]
  We propose a novel parallel decoding approach, namely textithidden transfer, which decodes multiple successive tokens simultaneously in a single forward pass. In terms of acceleration metrics, we outperform all the single-model acceleration techniques, including Medusa and Self-Speculative decoding.
  arXiv  Detail & Related papers  (2024-04-18T09:17:06Z)
• Advancing Beyond Identification: Multi-bit Watermark for Large Language Models [31.066140913513035]
  We show the viability of tackling misuses of large language models beyond the identification of machine-generated text. We propose Multi-bit Watermark via Position Allocation, embedding traceable multi-bit information during language model generation.
  arXiv  Detail & Related papers  (2023-08-01T01:27:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.