paper-with-me

홈 › Papers

Nearly Optimal Active Preference Learning and Its Application to LLM Alignment

2026-02-02 · Yao Zhao, Kwang-Sung Jun arxiv

Aligning large language models (LLMs) depends on high-quality datasets of human preference labels, which are costly to collect. Although active learning has been studied to improve sample efficiency relative to passive collection, many existing approaches adopt classical experimental design criteria such as G- or D-optimality. These objectives are not tailored to the structure of preference learning, leaving open the design of problem-specific algorithms. In this work, we identify a simple intuition specific to preference learning that calls into question the suitability of these existing design objectives. Motivated by this insight, we propose two active learning algorithms. The first provides the first instance-dependent label complexity guarantee for this setting, and the second is a simple, practical greedy method. We evaluate our algorithm on real-world preference datasets and observe improved sample efficiency compared to existing methods.

📄 PDF Abstract BibTeX arXiv:2602.01581

Code (0)

등록된 구현이 없습니다.

Tasks

Active Learning

Similar Papers 제목 키워드 기반

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

A Nearly Instance Optimal Algorithm for Top-k Ranking under the Multinomial Logit Model

2017-07-25 · Xi Chen, Yuanzhi Li, Jieming Mao

We study the active learning problem of top-$k$ ranking from multi-wise comparisons under the popular multinomial logit model. Our goal is to identify the top-$k$ items with high probability by adaptively querying sets f…

Active Learning

Active Learning Ranking from Pairwise Preferences with Almost Optimal Query Complexity

2011-12-01 · NeurIPS 2011 12 · Nir Ailon

Given a set $V$ of $n$ elements we wish to linearly order them using pairwise preference labels which may be non-transitive (due to irrationality or arbitrary noise). The goal is to linearly order the elements while d…

Active LearningLearning-To-Rank

Sample Efficient Preference Alignment in LLMs via Active Exploration

2023-12-01 · Viraj Mehta, Syrine Belakaria, Vikramjeet Das, Ojash Neopane 외

Preference-based feedback is important for many applications in machine learning where evaluation of a reward function is not feasible. Notable recent examples arise in preference alignment for large language models, inc…

reinforcement-learningReinforcement Learning

PrefDisco: Benchmarking Proactive Personalized Reasoning

2025-09-30 · Shuyue Stella Li, Avinandan Bose, Faeze Brahman, Simon Shaolei Du 외 arxiv

Current large language model (LLM) development treats task-solving and preference-alignment as separate challenges, optimizing first for objective correctness, then for alignment to aggregated human preferences. This par…