paper-with-me

Papers

GumbelSoft: Diversified Language Model Watermarking via the GumbelMax-trick

2024-02-20 · Jiayi Fu, Xuandong Zhao, Ruihan Yang, Yuansen Zhang, Jiangjie Chen, Yanghua Xiao

Large language models (LLMs) excellently generate human-like text, but also raise concerns about misuse in fake news and academic dishonesty. Decoding-based watermark, particularly the GumbelMax-trick-based watermark(GM watermark), is a standout solution for safeguarding machine-generated texts due to its notable detectability. However, GM watermark encounters a major challenge with generation diversity, always yielding identical outputs for the same prompt, negatively impacting generation diversity and user experience. To overcome this limitation, we propose a new type of GM watermark, the Logits-Addition watermark, and its three variants, specifically designed to enhance diversity. Among these, the GumbelSoft watermark (a softmax variant of the Logits-Addition watermark) demonstrates superior performance in high diversity settings, with its AUROC score outperforming those of the two alternative variants by 0.1 to 0.3 and surpassing other decoding-based watermarking methods by a minimum of 0.1.

📄 PDF Abstract BibTeX arXiv:2402.12948

Code (1)

poruna-byte/gumbelsoft 공식 구현

Tasks

DiversityLanguage ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Watermarking Discrete Diffusion Language Models

2025-11-03 · Avi Bagchi, Akhil Bhimaraju, Moulik Choraria, Daniel Alabi 외 arxiv

Watermarking has emerged as a promising technique to track AI-generated content and differentiate it from authentic human creations. While prior work extensively studies watermarking for autoregressive large language mod…

Theoretically Grounded Framework for LLM Watermarking: A Distribution-Adaptive Approach

2024-10-03 · Haiyun He, Yepeng Liu, Ziqiao Wang, Yongyi Mao 외

Watermarking has emerged as a crucial method to distinguish AI-generated text from human-created text. In this paper, we present a novel theoretical framework for watermarking Large Language Models (LLMs) that jointly op…

On Evaluating The Performance of Watermarked Machine-Generated Texts Under Adversarial Attacks

2024-07-05 · Zesen Liu, Tianshuo Cong, Xinlei He, Qi Li

Large Language Models (LLMs) excel in various applications, including text generation and complex tasks. However, the misuse of LLMs raises concerns about the authenticity and ethical implications of the content they pro…

Face SwappingText Generation

Superior Performance with Diversified Strategic Control in FPS Games Using General Reinforcement Learning

2021-09-29 · Shuxing Li, Jiawei Xu, Chun Yuan, Peng Sun 외

This paper offers an overall solution for first-person shooter (FPS) games to achieve superior performance using general reinforcement learning (RL). We introduce an agent in ViZDoom that can surpass previous top agents …

FPS GamesGeneral Reinforcement Learningreinforcement-learningReinforcement Learning (RL)

MetaSeal: Defending Against Image Attribution Forgery Through Content-Dependent Cryptographic Watermarks

2025-09-13 · Tong Zhou, Ruyi Ding, Gaowen Liu, Charles Fleming 외 arxiv

The rapid growth of digital and AI-generated images has amplified the need for secure and verifiable methods of image attribution. While digital watermarking offers more robust protection than metadata-based approaches--…

Image Attribution