Impact of Human Preference Alignment on LLM Robustness to Adversarial Prompts Across Domains

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 the alignment of LLMs with human preferences (e.g., via RLHF or DPO) influence their robustness to adversarial prompts across different domains, as measured by perplexity and task-specific accuracy on benchmarks like AdvBench or AlpacaEval?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 7.7/10.