Semantic Self-Guided Watermarking with Enhanced Text Quality for Large Language Models

ACL ARR 2025 February Submission5170 Authors

Abstract: The rapid development of large language models (LLMs) has created an urgent need for identifying machine-generated texts, and text watermarking technology has proven to be an effective solution. However, current watermarking methods, while demonstrating strong detectability, significantly degrade text quality due to the introduction of unnatural tokens. The main reason lies in the fact that these methods ignore the importance of semantic information in the watermarking process. To address this issue, we note that the logit vector produced by LLMs encodes both semantic understanding of input texts and prediction confidence across different tokens. Therefore, we propose a novel Semantic Self-Guided Watermarking (SSGW) framework that leverages the LLM itself to generate a guidance logic vector that assists in watermarking while producing the original one concurrently. Subsequently, we design a transform module to analyze these two vectors comprehensively and then transform them into adaptive watermark logits for different candidate tokens, thereby reducing the possibility of selecting inappropriate tokens. Experimental results confirm the effectiveness of our method in achieving superior performance in both watermark detectability and text quality preservation. The source code will be made publicly available upon acceptance.

Paper Type: Long

Research Area: NLP Applications

Research Area Keywords: rumor/misinformation detection,security/privacy

Contribution Types: NLP engineering experiment

Languages Studied: English

Submission Number: 5170