English
Related papers

Related papers: SAEMark: Steering Personalized Multilingual LLM Wa…

200 papers

The rapid advancement of large language models (LLMs) has raised concerns regarding their potential misuse, particularly in generating fake news and misinformation. To address these risks, watermarking techniques for autoregressive language…

Cryptography and Security · Computer Science 2025-06-24 Koichi Nagatsuka , Terufumi Morishita , Yasuhiro Sogawa

Sparse autoencoders (SAEs) are a popular method for interpreting concepts represented in large language model (LLM) activations. However, there is a lack of evidence regarding the validity of their interpretations due to the lack of a…

Machine Learning · Computer Science 2025-02-25 Subhash Kantamneni , Joshua Engels , Senthooran Rajamanoharan , Max Tegmark , Neel Nanda

Large language model (LLM) watermarking has emerged as a promising approach for detecting and attributing AI-generated text, yet its robustness to black-box spoofing remains insufficiently evaluated. Existing evaluation methods often demand…

Cryptography and Security · Computer Science 2026-04-14 Hanbo Huang , Xuan Gong , Yiran Zhang , Hao Zheng , Shiyu Liang

Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting large language models (LLMs) by decomposing token activations into combinations of human-understandable features. While SAEs provide crucial insights into LLM…

Machine Learning · Computer Science 2025-11-11 Zhen Xu , Zhen Tan , Song Wang , Kaidi Xu , Tianlong Chen

With the increasing use of large-language models (LLMs) like ChatGPT, watermarking has emerged as a promising approach for tracing machine-generated content. However, research on LLM watermarking often relies on simple perplexity or…

Computation and Language · Computer Science 2023-12-06 Karanpartap Singh , James Zou

We demonstrate that while the current approaches for language model watermarking are effective for open-ended generation, they are inadequate at watermarking LM outputs for constrained generation tasks with low-entropy output spaces.…

Cryptography and Security · Computer Science 2026-01-21 Nghia T. Le , Alan Ritter , Kartik Goyal

In the present-day scenario, Large Language Models (LLMs) are establishing their presence as powerful instruments permeating various sectors of society. While their utility offers valuable support to individuals, there are multiple concerns…

Computation and Language · Computer Science 2025-07-01 Badr Youbi Idrissi , Monica Millunzi , Amelia Sorrenti , Lorenzo Baraldi , Daryna Dementieva

Watermarking is an important tool for promoting the responsible use of large language models (LLMs). Existing watermarks insert a signal into generated tokens that either flags LLM-generated text (zero-bit watermarking) or encodes more…

Machine Learning · Computer Science 2026-05-25 Atefeh Gilani , Sajani Vithana , Carol Xuan Long , Oliver Kosut , Lalitha Sankar , Flavio P. Calmon

Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but controlling their behavior reliably remains challenging, especially in open-ended generation settings. This paper…

Computation and Language · Computer Science 2025-12-08 Zirui He , Mingyu Jin , Bo Shen , Ali Payani , Yongfeng Zhang , Mengnan Du

To mitigate the potential harms of Large Language Models (LLMs)generated text, researchers have proposed watermarking, a process of embedding detectable signals within text. With watermarking, we can always accurately detect LLM-generated…

Computation and Language · Computer Science 2025-11-19 William Guo , Adaku Uchendu , Ana Smith

In recent years, large language models (LLMs) have achieved remarkable performances in various NLP tasks. They can generate texts that are indistinguishable from those written by humans. Such remarkable performance of LLMs increases their…

Computation and Language · Computer Science 2025-02-18 Yuki Takezawa , Ryoma Sato , Han Bao , Kenta Niwa , Makoto Yamada

Sparse autoencoders (SAEs) provide a powerful mechanism for decomposing the dense representations produced by Large Language Models (LLMs) into interpretable latent features. We posit that SAEs constitute a natural foundation for Learned…

Machine Learning · Computer Science 2026-03-17 Thibault Formal , Maxime Louis , Hervé Dejean , Stéphane Clinchant

The rapid development of Large Language Models (LLMs) has intensified concerns about content traceability and potential misuse. Existing watermarking schemes for sampled text often face trade-offs between maintaining text quality and…

Computation and Language · Computer Science 2025-04-17 Shizhan Cai , Liang Ding , Dacheng Tao

Potential harms of large language models can be mitigated by watermarking model output, i.e., embedding signals into generated text that are invisible to humans but algorithmically detectable from a short span of tokens. We propose a…

Machine Learning · Computer Science 2024-05-03 John Kirchenbauer , Jonas Geiping , Yuxin Wen , Jonathan Katz , Ian Miers , Tom Goldstein

Amidst rising concerns about the internet being proliferated with content generated from language models (LMs), watermarking is seen as a principled way to certify whether text was generated from a model. Many recent watermarking techniques…

Cryptography and Security · Computer Science 2024-11-11 Saksham Rastogi , Danish Pruthi

Large language models (LLMs) are pre-trained and post-trained on vast amounts of loosely curated data, raising the possibility that these models may have been trained on proprietary datasets or the same benchmarks used for evaluation. This…

Machine Learning · Computer Science 2026-05-11 Pengrun Huang , Kamalika Chaudhuri , Yu-Xiang Wang

Text watermarks in large language models (LLMs) are increasingly used to detect synthetic text, mitigating misuse cases like fake news and academic dishonesty. While existing watermarking detection techniques primarily focus on classifying…

Computation and Language · Computer Science 2025-06-13 Xuandong Zhao , Chenwen Liao , Yu-Xiang Wang , Lei Li

Watermarking technology is a method used to trace the usage of content generated by large language models. Sentence-level watermarking aids in preserving the semantic integrity within individual sentences while maintaining greater…

Computation and Language · Computer Science 2025-04-25 Junyan Zhang , Shuliang Liu , Aiwei Liu , Yubo Gao , Jungang Li , Xiaojie Gu , Xuming Hu

Watermarking has become a key technique for proprietary language models, enabling the distinction between AI-generated and human-written text. However, in many real-world scenarios, LLM-generated content may undergo post-generation edits,…

Machine Learning · Computer Science 2025-10-03 Liyan Xie , Muhammad Siddeek , Mohamed Seif , Andrea J. Goldsmith , Mengdi Wang

The widespread use of Large Language Models (LLMs) in text generation has raised increasing concerns about intellectual property disputes. Watermarking techniques, which embed meta information into AI-generated content (AIGC), have the…

Cryptography and Security · Computer Science 2026-04-15 Shangkun Che , Silin Du , Ge Gao
‹ Prev 1 3 4 5 6 7 10 Next ›