Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

8-2024

Abstract

Text watermarking has emerged as a pivotal technique for identifying machine-generated text. However, existing methods often rely on arbitrary vocabulary partitioning during decoding to embed watermarks, which compromises the availability of suitable tokens and significantly degrades the quality of responses. This study assesses the impact of watermarking on different capabilities of large language models (LLMs) from a cognitive science lens. Our finding highlights a significant disparity; knowledge recall and logical reasoning are more adversely affected than language generation. These results suggest a more profound effect of watermarking on LLMs than previously understood. To address these challenges, we introduce Watermarking with Mutual Exclusion (WatME), a novel approach leveraging linguistic prior knowledge of inherent lexical redundancy in LLM vocabularies to seamlessly integrate watermarks. Specifically, WatME dynamically optimizes token usage during the decoding process by applying a mutually exclusive rule to the identified lexical redundancies. This strategy effectively prevents the unavailability of appropriate tokens and preserves the expressive power of LLMs. We provide both theoretical analysis and empirical evidence showing that WatME effectively preserves the diverse capabilities of LLMs while ensuring watermark detectability.

Discipline

Databases and Information Systems | Programming Languages and Compilers

Research Areas

Data Science and Engineering

Publication

Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, Bangkok, Thailand, 2024 August 11-16

First Page

9166

Last Page

9180

Publisher

ACL

City or Country

USA

Additional URL

https://aclanthology.org/2024.acl-long.496

Download

Share

COinS