相关论文: ACTG-ARL: Differentially Private Conditional Text …

Retrieval-Augmented Generation (RAG) enhances the utility of Large Language Models (LLMs) by retrieving external documents. Since the knowledge databases in RAG are predominantly utilized via cloud services, private data in sensitive…

The recently introduced Controlled Text Reduction (CTR) task isolates the text generation step within typical summarization-style tasks. It does so by challenging models to generate coherent text conforming to pre-selected content within…

Ensuring that reinforcement learning (RL) controllers satisfy safety and reliability constraints in real-world settings remains challenging: state-avoidance and constrained Markov decision processes often fail to capture trajectory-level…

While data sharing is crucial for knowledge development, privacy concerns and strict regulation (e.g., European General Data Protection Regulation (GDPR)) unfortunately limits its full effectiveness. Synthetic tabular data emerges as an…

The rapid development of Artificial Intelligence (AI) has led to the creation of powerful text generation models, such as large language models (LLMs), which are widely used for diverse applications. However, concerns surrounding…

Open domain dialog systems face the challenge of being repetitive and producing generic responses. In this paper, we demonstrate that by conditioning the response generation on interpretable discrete dialog attributes and composed…

Large language models generate fluent texts and can follow natural language instructions to solve a wide range of tasks without task-specific training. Nevertheless, it is notoriously difficult to control their generation to satisfy the…

Differential privacy (DP) is one data protection avenue to safeguard user information used for training deep models by imposing noisy distortion on privacy data. Such a noise perturbation often results in a severe performance degradation in…

Deep Reinforcement Learning (DRL) has the potential to be used for synthesizing feedback controllers (agents) for various complex systems with unknown dynamics. These systems are expected to satisfy diverse safety and liveness properties…

Retrieval-augmented generation (RAG) is a powerful technique to facilitate language model with proprietary and private data, where data privacy is a pivotal concern. Whereas extensive research has demonstrated the privacy risks of large…

The widespread adoption of Retrieval-Augmented Generation (RAG) systems in real-world applications has heightened concerns about the confidentiality and integrity of their proprietary knowledge bases. These knowledge bases, which play a…

Reinforcement learning (RL) has emerged as a powerful paradigm for fine-tuning Large Language Models (LLMs) for text generation. In particular, recent LLMs such as ChatGPT and GPT-4 can engage in fluent conversations with users after…

We consider training models with differential privacy (DP) using mini-batch gradients. The existing state-of-the-art, Differentially Private Stochastic Gradient Descent (DP-SGD), requires privacy amplification by sampling or shuffling to…

The state-of-the-art for training on-device language models for mobile keyboard applications combines federated learning (FL) with differential privacy (DP) via the DP-Follow-the-Regularized-Leader (DP-FTRL) algorithm. Two variants of…

Language models are capable of memorizing detailed patterns and information, leading to a double-edged effect: they achieve impressive modeling performance on downstream tasks with the stored knowledge but also raise significant privacy…

Retrieval-Augmented Generation (RAG) enhances the factual accuracy of large language models (LLMs) by conditioning outputs on external knowledge sources. However, when retrieval involves private or sensitive data, RAG systems are…

Modern machine learning models heavily rely on large datasets that often include sensitive and private information, raising serious privacy concerns. Differentially private (DP) data generation offers a solution by creating synthetic…

Personalized text generation aims to infer users' writing style preferences from their historical texts and generate outputs that faithfully reflect these stylistic characteristics. Existing solutions primarily adopt two paradigms:…

Existing differentially private (DP) synthetic data generation mechanisms typically assume a single-source table. In practice, data is often distributed across multiple tables with relationships across tables. In this paper, we introduce…

Applying generative adversarial networks (GANs) to text-related tasks is challenging due to the discrete nature of language. One line of research resolves this issue by employing reinforcement learning (RL) and optimizing the next-word…