Multimodal Large Language Models (MLLMs) already achieve state-of-the-art results across a wide range of tasks and modalities. To push their reasoning ability further, recent studies explore advanced prompting schemes and post-training fine-tuning. Although these techniques improve logical accuracy, they frequently leave the models' outputs burdened with pronounced social biases. Clarifying how reasoning gains interact with bias mitigation-and whether the two objectives inherently trade off-therefore remains an open and pressing research problem. Our study begins by benchmarking three bias-mitigation strategies-supervised fine-uning (SFT), knowledge distillation (KD), and rule-based reinforcement learning (RL)-under identical conditions, establishing their baseline strengths and weaknesses. Building on these results, we vary the proportion of debias-focused and reasoning-centric samples within each paradigm to chart the reasoning-versus-bias trade-off. Our sweeps reveal a consistent sweet spot: a roughly 1:4 mix trained with reinforcement learning cuts stereotype scores by 10% while retaining 88% of the model's original reasoning accuracy, offering concrete guidance for balancing fairness and capability in MLLMs.
Pan et al. (Wed,) studied this question.