Comparative Analysis of Directional Preference Alignment and Scalar-Reward RLHF on HANS Under Adversarial Syntactic Distractors

Fine-grained control over large language models (LLMs) remains a significant challenge, hindering their adaptability to diverse user needs. While Reinforcement Learning from Human Feedback (RLHF) shows promise in aligning LLMs, its reliance on scalar rewards often limits its ability to capture diverse user preferences in real-world applications. To address this limitation, we introduce the Directional Preference Alignment (DPA) framework. Unlike the scalar-reward RLHF, DPA incorporates multi-objective reward modeling to represent diverse preference profiles. Additionally, DPA models user prefe

Research goal: How does Directional Preference Alignment with multi-objective rewards compare to scalar-reward RLHF in terms of accuracy on the HANS benchmark when tested against adversarial syntactic distractors?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.5/10.