LGAIJul 22, 2024

Exploring and Addressing Reward Confusion in Offline Preference Learning

arXiv:2407.16025v21 citationsh-index: 10
Originality Incremental advance
AI Analysis

This addresses a critical issue in offline RLHF for AI alignment, though it appears incremental as it builds on existing preference learning frameworks.

The paper tackles the problem of reward confusion in offline Reinforcement Learning from Human Feedback (RLHF) caused by spurious correlations in training data, and proposes a method that significantly reduces this confusion by leveraging preference transitivity and active learning to build a global preference chain.

Spurious correlations in a reward model's training data can prevent Reinforcement Learning from Human Feedback (RLHF) from identifying the desired goal and induce unwanted behaviors. This paper shows that offline RLHF is susceptible to reward confusion, especially in the presence of spurious correlations in offline data. We create a benchmark to study this problem and propose a method that can significantly reduce reward confusion by leveraging transitivity of preferences while building a global preference chain with active learning.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes