Paper Reading AI Learner

X-Mark: Towards Lossless Watermarking Through Lexical Redundancy

2023-11-16 11:58:31
Liang Chen, Yatao Bian, Yang Deng, Shuaiyi Li, Bingzhe Wu, Peilin Zhao, Kam-fai Wong

Abstract

Text watermarking has emerged as an important technique for detecting machine-generated text. However, existing methods can severely degrade text quality due to arbitrary vocabulary partitioning, which disrupts the language model's expressiveness and impedes textual coherence. To mitigate this, we introduce XMark, a novel approach that capitalizes on text redundancy within the lexical space. Specifically, XMark incorporates a mutually exclusive rule for synonyms during the language model decoding process, thereby integrating prior knowledge into vocabulary partitioning and preserving the capabilities of language generation. We present theoretical analyses and empirical evidence demonstrating that XMark substantially enhances text generation fluency while maintaining watermark detectability. Furthermore, we investigate watermarking's impact on the emergent abilities of large language models, including zero-shot and few-shot knowledge recall, logical reasoning, and instruction following. Our comprehensive experiments confirm that XMark consistently outperforms existing methods in retaining these crucial capabilities of LLMs.

Abstract (translated)

文本水印作为一种重要的方法,用于检测由机器生成的文本。然而,现有的方法会严重破坏文本质量,因为随意词汇分割会破坏语言模型的表现力并阻碍文本的连贯性。为了减轻这种破坏,我们引入了XMark,一种新方法,它利用词汇空间中的文本冗余来 capitalize。具体来说,XMark 在语言模型解码过程中引入了互斥规则来处理同义词,从而将先验知识融入词汇分割中并保留语言生成能力。我们提供了理论分析和实证证据,证明 XMark 在保持水印检测的同时显著增强文本生成流畅度。此外,我们研究了水印对大型语言模型新兴能力的影响,包括零 shots和少数 shot 知识召回、推理和指令跟随。我们的全面实验证实,XMark 持续优于现有方法,保留 LLM 的关键功能。

URL

https://arxiv.org/abs/2311.09832

PDF

https://arxiv.org/pdf/2311.09832.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot