English
Related papers

Related papers: SAEMark: Steering Personalized Multilingual LLM Wa…

200 papers

We study the problem of watermarking large language models (LLMs) generated text -- one of the most promising approaches for addressing the safety challenges of LLM usage. In this paper, we propose a rigorous theoretical framework to…

Computation and Language · Computer Science 2023-10-16 Xuandong Zhao , Prabhanjan Ananth , Lei Li , Yu-Xiang Wang

Multilingual watermarking aims to make large language model (LLM) outputs traceable across languages, yet current methods still fall short. Despite claims of cross-lingual robustness, they are evaluated only on high-resource languages. We…

Computation and Language · Computer Science 2026-03-26 Asim Mohamed , Martin Gubri

Latent Diffusion Models (LDMs) have established themselves as powerful tools in the rapidly evolving field of image generation, capable of producing highly realistic images. However, their widespread adoption raises critical concerns about…

Cryptography and Security · Computer Science 2026-01-28 Zhonghao Yang , Linye Lyu , Xuanhang Chang , Daojing He , YU LI

Model internals encode rich information about how a large language model (LLM) processes its training data; however, post-training data engineering largely relies on external signals and ignores rich intrinsic signals lying in model…

Machine Learning · Computer Science 2026-05-27 Yi Jing , Zao Dai , Jinwu Hu , Zijun Yao , Lei Hou , Juanzi Li , Xiaozhi Wang

In this paper, we investigate the recent state-of-the-art schemes for watermarking large language models (LLMs) outputs. These techniques are claimed to be robust, scalable and production-grade, aimed at promoting responsible usage of LLMs.…

Cryptography and Security · Computer Science 2026-05-11 Jonathan Hong Jin Ng , Anh Tu Ngo , Anupam Chattopadhyay

Text watermarking for large language models (LLMs) enables model owners to verify text origin and protect intellectual property. While watermarking methods for closed-source LLMs are relatively mature, extending them to open-source models…

Cryptography and Security · Computer Science 2025-10-29 Jiaqi Xue , Yifei Zhao , Mansour Al Ghanim , Shangqian Gao , Ruimin Sun , Qian Lou , Mengxin Zheng

Large language models (LLMs) show strong multilingual capabilities, yet reliably controlling the language of their outputs remains difficult. Representation-level steering addresses this by adding language-specific vectors to model…

Computation and Language · Computer Science 2026-04-07 Sing Hieng Wong , Hassan Sajjad , A. B. Siddique

As large language models (LLMs) generate increasingly human-like text, watermarking has emerged as a promising solution for reliable attribution beyond mere detection. While multi-bit watermarking enables richer provenance encoding,…

Computation and Language · Computer Science 2026-05-11 Yidan Wang , Yubing Ren , Yanan Cao , Li Guo

The recent explosion of high-quality language models has necessitated new methods for identifying AI-generated text. Watermarking is a leading solution and could prove to be an essential tool in the age of generative AI. Existing approaches…

Cryptography and Security · Computer Science 2024-10-25 Miranda Christ , Sam Gunn , Tal Malkin , Mariana Raykova

Large Language Models (LLMs) are traditionally viewed as black-box algorithms, therefore reducing trustworthiness and obscuring potential approaches to increasing performance on downstream tasks. In this work, we apply an effective LLM…

Computation and Language · Computer Science 2025-07-10 Shun Wang , Tyler Loakman , Youbo Lei , Yi Liu , Bohao Yang , Yuting Zhao , Dong Yang , Chenghua Lin

We introduce the first watermark tailored for diffusion language models (DLMs), an emergent LLM paradigm able to generate tokens in arbitrary order, in contrast to standard autoregressive language models (ARLMs) which generate tokens…

Machine Learning · Computer Science 2026-02-20 Thibaud Gloaguen , Robin Staab , Nikola Jovanović , Martin Vechev

The widely adopted and powerful generative large language models (LLMs) have raised concerns about intellectual property rights violations and the spread of machine-generated misinformation. Watermarking serves as a promising approch to…

Cryptography and Security · Computer Science 2024-10-28 Ruisi Zhang , Farinaz Koushanfar

LLM watermarks must be detectable without compromising text quality, yet most existing schemes bias the next-token distribution and pay for detection with measurable quality loss. We present SLAM (Structural Linguistic Activation Marking),…

Computation and Language · Computer Science 2026-05-12 Fabrice Harel-Canada , Amit Sahai

As large language models (LLMs) grow in scale and capability, understanding their internal mechanisms becomes increasingly critical. Sparse autoencoders (SAEs) have emerged as a key tool in mechanistic interpretability, enabling the…

Computation and Language · Computer Science 2025-06-10 Jiaming Li , Haoran Ye , Yukun Chen , Xinyue Li , Lei Zhang , Hamid Alinejad-Rokny , Jimmy Chih-Hsien Peng , Min Yang

Large language models (LLMs) have demonstrated powerful capabilities in both text understanding and generation. Companies have begun to offer Embedding as a Service (EaaS) based on these LLMs, which can benefit various natural language…

Computation and Language · Computer Science 2023-06-05 Wenjun Peng , Jingwei Yi , Fangzhao Wu , Shangxi Wu , Bin Zhu , Lingjuan Lyu , Binxing Jiao , Tong Xu , Guangzhong Sun , Xing Xie

Text watermarks in large language models (LLMs) are an increasingly important tool for detecting synthetic text and distinguishing human-written content from LLM-generated text. While most existing studies focus on determining whether…

Machine Learning · Statistics 2025-06-30 Xiang Li , Garrett Wen , Weiqing He , Jiayuan Wu , Qi Long , Weijie J. Su

Sparse autoencoders (SAEs) promise a unified approach for mechanistic interpretability, concept discovery, and model steering in LLMs and LVLMs. However, realizing this potential requires learned features to be both interpretable and…

Machine Learning · Computer Science 2026-04-01 Akshay Kulkarni , Tsui-Wei Weng , Vivek Narayanaswamy , Shusen Liu , Wesam A. Sakla , Kowshik Thopalli

Training large language models (LLMs) from scratch requires significant computational resources, driving interest in developing smaller, domain-specific LLMs that maintain both efficiency and strong task performance. Medium-sized models…

Computation and Language · Computer Science 2026-03-02 Chaitali Bhattacharyya , Hyunsei Lee , Junyoung Lee , Shinhyoung Jang , Il hong Suh , Yeseong Kim

Sparse Autoencoders (SAEs) have emerged as a powerful unsupervised method for extracting sparse representations from language models, yet scalable training remains a significant challenge. We introduce a suite of 256 SAEs, trained on each…

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