English
Related papers

Related papers: Privacy-Preserving Reinforcement Learning from Hum…

200 papers

Differential privacy comes equipped with multiple analytical tools for the design of private data analyses. One important tool is the so-called "privacy amplification by subsampling" principle, which ensures that a differentially private…

Machine Learning · Computer Science 2018-11-26 Borja Balle , Gilles Barthe , Marco Gaboardi

Reinforcement Learning from Human Feedback (RLHF) has become a popular approach to align language models (LMs) with human preferences. This method involves collecting a large dataset of human pairwise preferences across various text…

Machine Learning · Computer Science 2024-10-24 Antoine Scheid , Etienne Boursier , Alain Durmus , Michael I. Jordan , Pierre Ménard , Eric Moulines , Michal Valko

Many commonly used learning algorithms work by iteratively updating an intermediate solution using one or a few data points in each iteration. Analysis of differential privacy for such algorithms often involves ensuring privacy of each step…

Machine Learning · Computer Science 2018-12-12 Vitaly Feldman , Ilya Mironov , Kunal Talwar , Abhradeep Thakurta

Fairness and privacy are two important values machine learning (ML) practitioners often seek to operationalize in models. Fairness aims to reduce model bias for social/demographic sub-groups. Privacy via differential privacy (DP)…

Machine Learning · Computer Science 2024-02-08 Sanjari Srivastava , Piotr Mardziel , Zhikhun Zhang , Archana Ahlawat , Anupam Datta , John C Mitchell

Existing approaches to language model alignment often treat safety as a tradeoff against helpfulness, which can lead to unacceptable responses in sensitive domains. To ensure reliable performance in such settings, we propose High-Confidence…

Machine Learning · Computer Science 2025-06-11 Yaswanth Chittepu , Blossom Metevier , Will Schwarzer , Austin Hoag , Scott Niekum , Philip S. Thomas

Re-inforcement learning from human feedback (RLHF) has been effective in the task of AI alignment. However, one of the key assumptions of RLHF is that the annotators (referred to as workers from here on out) have a homogeneous response…

Human-Computer Interaction · Computer Science 2026-01-29 Sarvesh Shashidhar , Abhishek Mishra , Madhav Kotecha

When users submit queries to Large Language Models (LLMs), their prompts can often contain sensitive data, forcing a difficult choice: Send the query to a powerful proprietary LLM providers to achieving state-of-the-art performance and risk…

Cryptography and Security · Computer Science 2026-04-21 Zheng Hui , Yijiang River Dong , Sanhanat Sivapiromrat , Ehsan Shareghi , Nigel Collier

We give simpler, sparser, and faster algorithms for differentially private fine-tuning of large-scale pre-trained language models, which achieve the state-of-the-art privacy versus utility tradeoffs on many standard NLP tasks. We propose a…

Differentially private gradient descent (DP-GD) is a popular algorithm to train deep learning models with provable guarantees on the privacy of the training data. In the last decade, the problem of understanding its performance cost with…

Machine Learning · Statistics 2025-05-29 Simone Bombari , Marco Mondelli

In this paper, we take a step towards a deeper understanding of learning from human preferences by systematically comparing the paradigm of reinforcement learning from human feedback (RLHF) with the recently proposed paradigm of direct…

Machine Learning · Computer Science 2024-06-06 Andi Nika , Debmalya Mandal , Parameswaran Kamalaruban , Georgios Tzannetos , Goran Radanović , Adish Singla

Reinforcement learning from human feedback (RLHF) emerges as a promising paradigm for aligning large language models (LLMs). However, a notable challenge in RLHF is overoptimization, where beyond a certain threshold, the pursuit of higher…

Machine Learning · Computer Science 2024-01-02 Yuanzhao Zhai , Han Zhang , Yu Lei , Yue Yu , Kele Xu , Dawei Feng , Bo Ding , Huaimin Wang

Reward models (RMs) are essential for aligning large language models (LLMs) with human preferences to improve interaction quality. However, the real world is pluralistic, which leads to diversified human preferences with respect to…

Computation and Language · Computer Science 2023-09-18 Pengyu Cheng , Jiawen Xie , Ke Bai , Yong Dai , Nan Du

The tension between data privacy and model utility has become the defining bottleneck for the practical deployment of large language models (LLMs) trained on sensitive corpora including healthcare. Differentially private stochastic gradient…

Machine Learning · Computer Science 2025-07-31 Afshin Khadangi , Amir Sartipi , Igor Tchappi , Ramin Bahmani , Gilbert Fridgen

Privacy-preserving data analysis is a rising challenge in contemporary statistics, as the privacy guarantees of statistical methods are often achieved at the expense of accuracy. In this paper, we investigate the tradeoff between…

Machine Learning · Statistics 2020-11-11 T. Tony Cai , Yichen Wang , Linjun Zhang

AI agents are commonly aligned with "human values" through reinforcement learning from human feedback (RLHF), where a single reward model is learned from aggregated human feedback and used to align an agent's behavior. However, human values…

Artificial Intelligence · Computer Science 2025-06-24 Carter Blair , Kate Larson , Edith Law

A centerpiece of the ever-popular reinforcement learning from human feedback (RLHF) approach to fine-tuning autoregressive language models is the explicit training of a reward model to emulate human feedback, distinct from the language…

Computation and Language · Computer Science 2023-05-22 Wanqiao Xu , Shi Dong , Dilip Arumugam , Benjamin Van Roy

Fine-tuning large language models (LLMs) has become an essential strategy for adapting them to specialized tasks; however, this process introduces significant privacy challenges, as sensitive training data may be inadvertently memorized and…

Cryptography and Security · Computer Science 2025-05-02 Hao Du , Shang Liu , Yang Cao

While large language models demonstrate remarkable capabilities, they often present challenges in terms of safety, alignment with human values, and stability during training. Here, we focus on two prevalent methods used to align these…

Computation and Language · Computer Science 2023-10-26 Gabriel Mukobi , Peter Chatain , Su Fong , Robert Windesheim , Gitta Kutyniok , Kush Bhatia , Silas Alberti

Personalized large language models (LLMs) are designed to tailor responses to individual user preferences. While Reinforcement Learning from Human Feedback (RLHF) is a commonly used framework for aligning LLMs with human preferences,…

Computation and Language · Computer Science 2024-12-10 Xinyu Li , Ruiyang Zhou , Zachary C. Lipton , Liu Leqi

We propose and analyze algorithms to solve a range of learning tasks under user-level differential privacy constraints. Rather than guaranteeing only the privacy of individual samples, user-level DP protects a user's entire contribution ($m…

Machine Learning · Computer Science 2021-12-06 Daniel Levy , Ziteng Sun , Kareem Amin , Satyen Kale , Alex Kulesza , Mehryar Mohri , Ananda Theertha Suresh