English
Related papers

Related papers: Differentially-private text generation degrades ou…

200 papers

Collecting high-quality training data is essential for fine-tuning Large Language Models (LLMs). However, acquiring such data is often costly and time-consuming, especially for non-English languages such as Italian. Recently, researchers…

Computation and Language · Computer Science 2025-04-01 Fatemeh Mohammadi , Tommaso Romano , Samira Maghool , Paolo Ceravolo

Positioned between pre-training and user deployment, aligning large language models (LLMs) through reinforcement learning (RL) has emerged as a prevailing strategy for training instruction following-models such as ChatGPT. In this work, we…

Machine Learning · Computer Science 2024-05-06 Fan Wu , Huseyin A. Inan , Arturs Backurs , Varun Chandrasekaran , Janardhan Kulkarni , Robert Sim

Recent literature has seen a considerable uptick in $\textit{Differentially Private Natural Language Processing}$ (DP NLP). This includes DP text privatization, where potentially sensitive input texts are transformed under DP to achieve…

Computation and Language · Computer Science 2025-03-13 Stephen Meisenbacher , Alexandra Klymenko , Alexander Karpp , Florian Matthes

The generative Artificial Intelligence (AI) tools based on Large Language Models (LLMs) use billions of parameters to extensively analyse large datasets and extract critical private information such as, context, specific details,…

Cryptography and Security · Computer Science 2023-10-20 Imdad Ullah , Najm Hassan , Sukhpal Singh Gill , Basem Suleiman , Tariq Ahamed Ahanger , Zawar Shah , Junaid Qadir , Salil S. Kanhere

As privacy gains traction in the NLP community, researchers have started adopting various approaches to privacy-preserving methods. One of the favorite privacy frameworks, differential privacy (DP), is perhaps the most compelling thanks to…

Computation and Language · Computer Science 2025-08-14 Ivan Habernal

Synthetic data from generative models emerges as the privacy-preserving data sharing solution. Such a synthetic data set shall resemble the original data without revealing identifiable private information. Till date, the prior focus on…

Machine Learning · Computer Science 2025-07-23 Chaoyi Zhu , Jiayi Tang , Juan F. Pérez , Marten van Dijk , Lydia Y. Chen

Large Language Models (LLMs) are now capable of generating highly fluent, human-like text. They enable many applications, but also raise concerns such as large scale spam, phishing, or academic misuse. While much work has focused on…

Computation and Language · Computer Science 2026-04-16 Swati Rallapalli , Shannon Gallagher , Ronald Yurko , Tyler Brooks , Chuck Loughin , Michele Sezgin , Violet Turri

We address the challenge of sample efficiency in differentially private fine-tuning of large language models (LLMs) using DP-SGD. While DP-SGD provides strong privacy guarantees, the added noise significantly increases the entropy of…

Machine Learning · Computer Science 2026-01-12 Ali Dadsetan , Frank Rudzicz

Large Language Models (LLM) are already widely used to generate content for a variety of online platforms. As we are not able to safely distinguish LLM-generated content from human-produced content, LLM-generated content is used to train…

Machine Learning · Computer Science 2024-06-18 Martin Briesch , Dominik Sobania , Franz Rothlauf

A common goal of privacy research is to release synthetic data that satisfies a formal privacy guarantee and can be used by an analyst in place of the original data. To achieve reasonable accuracy, a synthetic data set must be tuned to…

Databases · Computer Science 2015-03-20 Chao Li , Gerome Miklau

Scaling laws have emerged as important components of large language model (LLM) training as they can predict performance gains through scale, and provide guidance on important hyper-parameter choices that would otherwise be expensive. LLMs…

Protecting patient privacy in clinical narratives is essential for enabling secondary use of healthcare data under regulations such as GDPR and HIPAA. While manual de-identification remains the gold standard, it is costly and slow,…

Cryptography and Security · Computer Science 2026-04-24 Michele Miranda , Xinlan Yan , Nishant Mishra , Rachel Murphy , Ameen Abu-Hanna , Sébastien Bratières , Iacer Calixto

Large scale adoption of large language models has introduced a new era of convenient knowledge transfer for a slew of natural language processing tasks. However, these models also run the risk of undermining user trust by exposing unwanted…

Computation and Language · Computer Science 2022-04-21 Richard Plant , Valerio Giuffrida , Dimitra Gkatzia

Data privacy is a core tenet of responsible computing, and in the United States, differential privacy (DP) is the dominant technical operationalization of privacy-preserving data analysis. With this study, we qualitatively examine one class…

Human-Computer Interaction · Computer Science 2024-12-18 Lucas Rosenblatt , Bill Howe , Julia Stoyanovich

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by retrieving documents from an external corpus at inference time. When this corpus contains sensitive information, however, unprotected RAG systems are at risk of…

Machine Learning · Computer Science 2025-11-12 Ruihan Wu , Erchi Wang , Zhiyuan Zhang , Yu-Xiang Wang

The rapid advancements in large language models (LLMs) have significantly improved their ability to generate natural language, making texts generated by LLMs increasingly indistinguishable from human-written texts. Recent research has…

Computation and Language · Computer Science 2024-12-05 Sergio E. Zanotto , Segun Aroyehun

Large language models (LLMs) are increasingly integrated into real-time machine learning applications, where safeguarding user privacy is paramount. Traditional differential privacy mechanisms often struggle to balance privacy and accuracy,…

Cryptography and Security · Computer Science 2024-10-04 Jessica Smith , David Williams , Emily Brown

Differentially-private mechanisms for text generation typically add carefully calibrated noise to input words and use the nearest neighbor to the noised input as the output word. When the noise is small in magnitude, these mechanisms are…

Computation and Language · Computer Science 2021-04-27 Zekun Xu , Abhinav Aggarwal , Oluwaseyi Feyisetan , Nathanael Teissier

Diffusion models (DMs) are one of the most widely used generative models for producing high quality images. However, a flurry of recent papers points out that DMs are least private forms of image generators, by extracting a significant…

Machine Learning · Statistics 2025-03-06 Michael F. Liu , Saiyue Lyu , Margarita Vinaroz , Mijung Park

One-size-fits-all large language models (LLMs) are increasingly being used to help people with their writing. However, the style these models are trained to write in may not suit all users or use cases. LLMs would be more useful as writing…

Computation and Language · Computer Science 2024-09-10 Xinyue Liu , Harshita Diddee , Daphne Ippolito