Score: 1

On a Connection Between Imitation Learning and RLHF

Published: March 7, 2025 | arXiv ID: 2503.05079v1

By: Teng Xiao , Yige Yuan , Mingxiao Li and more

Potential Business Impact:

Teaches computers to follow human instructions better.

Business Areas:
Human Computer Interaction Design, Science and Engineering

This work studies the alignment of large language models with preference data from an imitation learning perspective. We establish a close theoretical connection between reinforcement learning from human feedback RLHF and imitation learning (IL), revealing that RLHF implicitly performs imitation learning on the preference data distribution. Building on this connection, we propose DIL, a principled framework that directly optimizes the imitation learning objective. DIL provides a unified imitation learning perspective on alignment, encompassing existing alignment algorithms as special cases while naturally introducing new variants. By bridging IL and RLHF, DIL offers new insights into alignment with RLHF. Extensive experiments demonstrate that DIL outperforms existing methods on various challenging benchmarks.

Country of Origin
🇺🇸 United States

Repos / Data Links

Page Count
16 pages

Category
Computer Science:
Machine Learning (CS)