📝 SummarXiv

Abstract

Alignment is vital for safely deploying large language models (LLMs). Existing techniques are either reward-based (train a reward model on preference pairs and optimize with reinforcement learning) or reward-free (directly fine-tune on ranked outputs). Recent research shows that well-tuned reward-based pipelines remain robust, and single-response demonstrations can outperform pairwise preference data. However, two challenges persist: (1) imbalanced safety datasets that overrepresent common hazards while neglecting long-tail threats; and (2) static reward models that ignore task difficulty, limiting optimization efficiency and attainable gains. We propose DR-IRL (Dynamically adjusting Rewards through Inverse Reinforcement Learning). We first train category-specific reward models using a balanced safety dataset covering seven harmful categories via IRL. Then we enhance Group Relative Policy Optimization (GRPO) by introducing dynamic reward scaling--adjusting rewards by task difficulty--data-level hardness by text encoder cosine similarity, model-level responsiveness by reward gaps. Extensive experiments across various benchmarks and LLMs demonstrate that DR-IRL outperforms all baseline methods in safety alignment while maintaining usefulness.