BPO: Staying Close to the Behavior LLM Creates Better Online LLM Alignment

TL;DR

This paper introduces online Preference Optimization (BPO), a method that improves large language model alignment by maintaining proximity to a behavior LLM, leading to significant performance gains across various tasks.

Contribution

The paper proposes a novel online DAP algorithm called BPO that emphasizes trust region construction to enhance LLM alignment, outperforming traditional offline methods.

Findings

BPO significantly improves performance on multiple tasks.

Online BPO increases win rates against human references.

Integrating BPO with existing DAP methods yields consistent gains.

Abstract

Direct alignment from preferences (DAP) has emerged as a promising paradigm for aligning large language models (LLMs) to human desiderata from pre-collected, offline preference datasets. While recent studies indicate that existing offline DAP methods can directly benefit from online training samples, we highlight the need to develop specific online DAP algorithms to fully harness the power of online training. Specifically, we identify that the learned LLM should adhere to the proximity of the behavior LLM, which collects the training samples. To this end, we propose online Preference Optimization in proximity to the Behavior LLM (BPO), emphasizing the importance of constructing a proper trust region for LLM alignment. We conduct extensive experiments to validate the effectiveness and applicability of our approach by integrating it with various DAP methods, resulting in significant performance improvements across a wide range of tasks when training with the same amount of preference data. Even when only introducing one additional data collection phase, our online BPO improves its offline DAP baseline from 72.0% to 80.2% on TL;DR and from 82.2% to 89.1% on Anthropic Helpfulness in terms of win rate against human reference text.