English
Related papers

Related papers: Source Attribution for Large Language Model-Genera…

200 papers

Watermarking algorithms for Large Language Models (LLMs) effectively identify machine-generated content by embedding and detecting hidden statistical features in text. However, such embedding leads to a decline in text quality, especially…

Cryptography and Security · Computer Science 2025-10-06 Yu Zhang , Shuliang Liu , Xu Yang , Xuming Hu

Watermarking has emerged as a promising solution for tracing and authenticating text generated by large language models (LLMs). A common approach to LLM watermarking is to construct a green/red token list and assign higher or lower…

Cryptography and Security · Computer Science 2025-10-27 Li An , Yujian Liu , Yepeng Liu , Yuheng Bu , Yang Zhang , Shiyu Chang

A recent and exciting thread of work focuses on developing methods for watermarking the output of large language models (LLMs). We focus on provably undetectable watermarking-that is, schemes that do not alter the output distribution of the…

Cryptography and Security · Computer Science 2026-04-15 Noam Mazor , Andrew Morgan , Rafael Pass

Watermarking by altering token sampling probabilities based on red-green list is a promising method for tracing the origin of text generated by large language models (LLMs). However, existing watermark methods often struggle with a…

Cryptography and Security · Computer Science 2025-05-21 Zongqi Wang , Tianle Gu , Baoyuan Wu , Yujiu Yang

We study the problem of multi-bit watermarking for large language models (LLMs). We introduce a block-autoregressive model inspired by multi-token prediction, in which the encoder has limited non-causal access to token distributions within…

Information Theory · Computer Science 2026-05-19 Sidong Guo , Tyler Kann , Teodora Baluta , Matthieu R. Bloch

Large language models (LLMs) learn a vast amount of knowledge during pretraining, but they are often oblivious to the source(s) of such knowledge. We investigate the problem of intrinsic source citation, where LLMs are required to cite the…

Computation and Language · Computer Science 2024-08-14 Muhammad Khalifa , David Wadden , Emma Strubell , Honglak Lee , Lu Wang , Iz Beltagy , Hao Peng

LLM watermarking, which embeds imperceptible yet algorithmically detectable signals in model outputs to identify LLM-generated text, has become crucial in mitigating the potential misuse of large language models. However, the abundance of…

Cryptography and Security · Computer Science 2024-10-29 Leyi Pan , Aiwei Liu , Zhiwei He , Zitian Gao , Xuandong Zhao , Yijian Lu , Binglin Zhou , Shuliang Liu , Xuming Hu , Lijie Wen , Irwin King , Philip S. Yu

Large language models (LLMs) such as GPT-4, PaLM, and Llama have significantly propelled the generation of AI-crafted text. With rising concerns about their potential misuse, there is a pressing need for AI-generated-text forensics. Neural…

Computation and Language · Computer Science 2023-08-15 Tharindu Kumarage , Huan Liu

Deep Learning (DL) models have caused a paradigm shift in our ability to comprehend raw data in various important fields, ranging from intelligence warfare and healthcare to autonomous transportation and automated manufacturing. A practical…

Cryptography and Security · Computer Science 2018-06-04 Bita Darvish Rouhani , Huili Chen , Farinaz Koushanfar

As large language models (LLMs) become integral to applications such as question answering and content creation, reliable content attribution has become increasingly important. Watermarking is a promising approach, but most existing methods…

Cryptography and Security · Computer Science 2026-05-11 Ya Jiang , Massieh Kordi Boroujeny , Surender Suresh Kumar , Kai Zeng

Deepfake speech attribution remains challenging for existing solutions. Classifier-based solutions often fail to generalize to domain-shifted samples, and watermarking-based solutions are easily compromised by distortions like codec…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-16 Wanying Ge , Xin Wang , Junichi Yamagishi

While large language models (LLMs) have shown remarkable capability to generate convincing text across diverse domains, concerns around its potential risks have highlighted the importance of understanding the rationale behind text…

Computation and Language · Computer Science 2024-04-03 Seongmin Lee , Zijie J. Wang , Aishwarya Chakravarthy , Alec Helbling , ShengYun Peng , Mansi Phute , Duen Horng Chau , Minsuk Kahng

We propose Easymark, a family of embarrassingly simple yet effective watermarks. Text watermarking is becoming increasingly important with the advent of Large Language Models (LLM). LLMs can generate texts that cannot be distinguished from…

Machine Learning · Computer Science 2023-10-16 Ryoma Sato , Yuki Takezawa , Han Bao , Kenta Niwa , Makoto Yamada

The growing deployment of Large Language Models (LLMs) has raised concerns about their misuse in generating harmful or deceptive content. To address this issue, watermarking methods have been proposed to embed identifiable multi-bit…

Computation and Language · Computer Science 2026-05-12 Jiahao Xu , Rui Hu , Olivera Kotevska , Zikai Zhang

Large language models (LLMs) memorize text from several sources of documents. In pretraining, LLM trains to maximize the likelihood of text but neither receives the source of the text nor memorizes the source. Accordingly, LLM can not…

Computation and Language · Computer Science 2024-07-19 Bumjin Park , Jaesik Choi

Several companies have deployed watermark-based detection to identify AI-generated content. However, attribution--the ability to trace back to the user of a generative AI (GenAI) service who created a given AI-generated content--remains…

Cryptography and Security · Computer Science 2026-01-28 Zhengyuan Jiang , Moyang Guo , Yuepeng Hu , Yupu Wang , Neil Zhenqiang Gong

Efficient knowledge injection methods for Large Language Models (LLMs), such as In-Context Learning, knowledge editing, and efficient parameter fine-tuning, significantly enhance model utility on downstream tasks. However, they also pose…

Cryptography and Security · Computer Science 2026-01-23 Ziwei Zhang , Juan Wen , Wanli Peng , Zhengxian Wu , Yinghan Zhou , Yiming Xue

Substantial research works have shown that deep models, e.g., pre-trained models, on the large corpus can learn universal language representations, which are beneficial for downstream NLP tasks. However, these powerful models are also…

Cryptography and Security · Computer Science 2024-07-16 Yixin Liu , Hongsheng Hu , Xun Chen , Xuyun Zhang , Lichao Sun

Text watermarking for Large Language Models (LLMs) has made significant progress in detecting LLM outputs and preventing misuse. Current watermarking techniques offer high detectability, minimal impact on text quality, and robustness to…

Cryptography and Security · Computer Science 2025-01-29 Aiwei Liu , Sheng Guan , Yiming Liu , Leyi Pan , Yifei Zhang , Liancheng Fang , Lijie Wen , Philip S. Yu , Xuming Hu

Large pre-trained language models (PLMs) have proven to be a crucial component of modern natural language processing systems. PLMs typically need to be fine-tuned on task-specific downstream datasets, which makes it hard to claim the…

Computation and Language · Computer Science 2023-02-13 Chenxi Gu , Chengsong Huang , Xiaoqing Zheng , Kai-Wei Chang , Cho-Jui Hsieh