← all papers · overview

Active Preference Optimization For Sample Efficient RLHF

Abstract

Large Language Models (LLMs) aligned using Reinforcement Learning from Human Feedback (RLHF) have shown remarkable generation abilities in numerous tasks. However, collecting high-quality human preferences creates costly bottlenecks in practical deployments, and hence, training data are often budgeted. In these scenarios, it is crucial to collect training data (e.g., contexts, a pair of generation

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).