paper-with-me

홈 › Papers

Contextual Online Uncertainty-Aware Preference Learning for Human Feedback

2025-04-27 · Nan Lu, Ethan X. Fang, Junwei Lu

Reinforcement Learning from Human Feedback (RLHF) has become a pivotal paradigm in artificial intelligence to align large models with human preferences. In this paper, we propose a novel statistical framework to simultaneously conduct the online decision-making and statistical inference on the optimal model using human preference data based on dynamic contextual information. Our approach introduces an efficient decision strategy that achieves both the optimal regret bound and the asymptotic distribution of the estimators. A key challenge in RLHF is handling the dependent online human preference outcomes with dynamic contexts. To address this, in the methodological aspect, we propose a two-stage algorithm starting with $\epsilon$-greedy followed by exploitations; in the theoretical aspect, we tailor anti-concentration inequalities and matrix martingale concentration techniques to derive the uniform estimation rate and asymptotic normality of the estimators using dependent samples from both stages. Extensive simulation results demonstrate that our method outperforms state-of-the-art strategies. We apply the proposed framework to analyze the human preference data for ranking large language models on the Massive Multitask Language Understanding dataset, yielding insightful results on the performance of different large language models for medical anatomy knowledge.

📄 PDF Abstract BibTeX arXiv:2504.19342

Code (0)

등록된 구현이 없습니다.

Tasks

Anatomy

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

TUR-DPO: Topology- and Uncertainty-Aware Direct Preference Optimization

2026-04-30 · Abdulhady Abas Abdullah, Fatemeh Daneshfar, Seyedali Mirjalili, Mourad Oussalah arxiv

Aligning large language models (LLMs) with human preferences is commonly done via reinforcement learning from human feedback (RLHF) with Proximal Policy Optimization (PPO) or, more simply, via Direct Preference Optimizat…

Reinforcement LearningMathematical ReasoningQuestion Answering

Prompt-Dependent Ranking of Large Language Models with Uncertainty Quantification

2026-02-11 · Angel Rodrigo Avelar Menendez, Yufeng Liu, Xiaowu Dai arxiv

Rankings derived from pairwise comparisons are central to many economic and computational systems. In the context of large language models (LLMs), rankings are typically constructed from human preference data and present…

Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknown

2024-10-01 · Xingzhou Lou, Dong Yan, Wei Shen, Yuzi Yan 외

Reward models (RM) play a critical role in aligning generations of large language models (LLM) to human expectations. However, prevailing RMs fail to capture the stochasticity within human preferences and cannot effectiv…

Uncertainty Quantification

STL-Based Motion Planning and Uncertainty-Aware Risk Analysis for Human-Robot Collaboration with a Multi-Rotor Aerial Vehicle

2025-09-12 · Giuseppe Silano, Amr Afifi, Martin Saska, Antonio Franchi arxiv

This paper presents a motion planning and risk analysis framework for enhancing human-robot collaboration with a Multi-Rotor Aerial Vehicle. The proposed method employs Signal Temporal Logic to encode key mission objecti…

Motion Planning

Provable Benefits of Policy Learning from Human Preferences in Contextual Bandit Problems

2023-07-24 · Xiang Ji, Huazheng Wang, Minshuo Chen, Tuo Zhao 외

For a real-world decision-making problem, the reward function often needs to be engineered or learned. A popular approach is to utilize human feedback to learn a reward function for training. The most straightforward way…

Decision MakingMulti-Armed Bandits