NaDRO: Leveraging Dual-Reward Strategies for LLMs Training on Noisy Data

Group Relative Policy Optimization (GRPO) fine-tuning has demonstrated significant enhancements in reasoning tasks. However, it often relies on high quality labeled dataset, which is typically difficult to obtain. To address this challenge, we introduce Noise-Aware Dual-Reward Optimization (NaDRO) to effectively enhances the training of Large Language Models (LLMs) under noisy or ambiguous supervision. NaDRO operates through two key components: (1) Preference-based Outcome Reward (POR),which makes a principled bias-variance tradeoff, reducing training variance by learning from robust preference rankings instead of overfitting to single-best estimates; and (2) Context Perception Reward (CPR) mechanism, which ensures that LLMs conduct necessary qualitative assessment of the current problem state to foster deeper situational understanding prior to decision-making.