paper-with-me

홈 › Papers

ActiveUltraFeedback: Efficient Preference Data Generation using Active Learning

2026-03-10 · Davit Melikidze, Marian Schneider, Jessica Lam, Martin Wertich, Ido Hakimi, Barna Pásztor, Andreas Krause arxiv

Reinforcement Learning from Human Feedback (RLHF) has become the standard for aligning Large Language Models (LLMs), yet its efficacy is bottlenecked by the high cost of acquiring preference data, especially in low-resource and expert domains. To address this, we introduce ACTIVEULTRAFEEDBACK, a modular active learning pipeline that leverages uncertainty estimates to dynamically identify the most informative responses for annotation. Our pipeline facilitates the systematic evaluation of standard response selection methods alongside DOUBLE REVERSE THOMPSON SAMPLING (DRTS) and DELTAUCB, two novel methods prioritizing response pairs with large predicted quality gaps, leveraging recent results showing that such pairs provide good signals for fine-tuning. Our experiments demonstrate that ACTIVEULTRAFEEDBACK yields high-quality datasets that lead to significant improvements in downstream performance, notably achieving comparable or superior results with as little as one-sixth of the annotated data relative to static baselines. Our pipeline is available at https://github.com/lasgroup/ActiveUltraFeedback and our preference datasets at https://huggingface.co/ActiveUltraFeedback.

📄 PDF Abstract BibTeX arXiv:2603.09692

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningActive Learning

Similar Papers 제목 키워드 기반

Batch Active Learning of Reward Functions from Human Preferences

2024-02-24 · Erdem Biyik, Nima Anari, Dorsa Sadigh

Data generation and labeling are often expensive in robot learning. Preference-based learning is a concept that enables reliable labeling by querying users with preference questions. Active querying methods are commonly …

Active LearningPoint Processes

Batch Active Preference-Based Learning of Reward Functions

2018-10-10 · Erdem Biyik, Dorsa Sadigh

Data generation and labeling are usually an expensive part of learning for robotics. While active learning methods are commonly used to tackle the former problem, preference-based learning is a concept that attempts to s…

Active Learning

Active Preference Optimization for Sample Efficient RLHF

2024-02-16 · Nirjhar Das, Souradip Chakraborty, Aldo Pacchiano, Sayak Ray Chowdhury

Reinforcement Learning from Human Feedback (RLHF) is pivotal in aligning Large Language Models (LLMs) with human preferences. Although aligned generative models have shown remarkable abilities in various tasks, their rel…

Active Learning

AMPO: Active Multi-Preference Optimization

2025-02-25 · Taneesh Gupta, Rahul Madhavan, Xuchao Zhang, Chetan Bansal 외

Multi-preference optimization enriches language-model alignment beyond pairwise preferences by contrasting entire sets of helpful and undesired responses, thereby enabling richer training signals for large language model…

Language ModelingLanguage Modelling

ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment

2025-05-25 · Xiaoqiang Lin, Arun Verma, Zhongxiang Dai, Daniela Rus 외

The recent success of using human preferences to align large language models (LLMs) has significantly improved their performance in various downstream tasks like question answering, mathematical reasoning, and code gener…

Code GenerationMathematical ReasoningQuestion Answering