CLAICRApr 6

XMark: Reliable Multi-Bit Watermarking for LLM-Generated Texts

arXiv:2604.0524226.21 citationsh-index: 10Has Code
Predicted impact top 35% in CL · last 90 daysOriginality Incremental advance
AI Analysis

This addresses the need for reliable watermarking to trace malicious LLM usage, representing a strong incremental improvement over existing methods.

The paper tackles the problem of embedding multi-bit watermarks in LLM-generated text to enable attribution and tracing, proposing XMark which significantly improves decoding accuracy while preserving text quality, outperforming prior methods in experiments.

Multi-bit watermarking has emerged as a promising solution for embedding imperceptible binary messages into Large Language Model (LLM)-generated text, enabling reliable attribution and tracing of malicious usage of LLMs. Despite recent progress, existing methods still face key limitations: some become computationally infeasible for large messages, while others suffer from a poor trade-off between text quality and decoding accuracy. Moreover, the decoding accuracy of existing methods drops significantly when the number of tokens in the generated text is limited, a condition that frequently arises in practical usage. To address these challenges, we propose \textsc{XMark}, a novel method for encoding and decoding binary messages in LLM-generated texts. The unique design of \textsc{XMark}'s encoder produces a less distorted logit distribution for watermarked token generation, preserving text quality, and also enables its tailored decoder to reliably recover the encoded message with limited tokens. Extensive experiments across diverse downstream tasks show that \textsc{XMark} significantly improves decoding accuracy while preserving the quality of watermarked text, outperforming prior methods. The code is at https://github.com/JiiahaoXU/XMark.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes