DSO：直接转向优化以减轻偏差
DSO: Direct Steering Optimization for Bias Mitigation
AI总结：
DSO通过强化学习优化激活转换，在VLMs和LLMs中实现公平性与能力的最佳平衡，提供推理时的偏见控制能力。
摘要：
生成模型经常被用来代表用户做出决策，例如视觉-语言模型（VLMs）识别房间中的医生以帮助视障人士。然而，VLM的决策受到输入中人们感知的种族属性的影响，这可能导致偏见的结果，如无法识别女性为医生。此外，当减少偏见导致性能损失时，用户可能对平衡偏见缓解与整体模型能力有不同需求，突显了需要在推理过程中能够控制偏见减少的方法的需求。激活转向是一种流行的推理时间可控性方法，已在诱导大型语言模型（LLMs）的安全行为方面显示出潜力。然而，我们发现当前的转向方法难以纠正偏见，其中需要在不同种族群体中产生等概率的结果。为了解决这个问题，我们提出了直接转向优化（DSO），它使用强化学习来寻找转向激活的线性变换，以减轻偏见同时保持对模型性能的控制。我们证明DSO在VLMs和LLMs上实现了公平性与能力之间的最佳权衡，同时为从业者提供了推理时间控制权衡的能力。总体而言，我们的工作强调了设计直接优化转向策略以控制模型行为的好处，提供了比依赖预定义启发式方法进行可控性的方法更有效的偏见干预。
英文摘要：
Generative models are often deployed to make decisions on behalf of users, such as vision-language models (VLMs) identifying which person in a room is a doctor to help visually impaired individuals. Yet, VLM decisions are influenced by the perceived demographic attributes of people in the input, which can lead to biased outcomes like failing to identify women as doctors. Moreover, when reducing bias leads to performance loss, users may have varying needs for balancing bias mitigation with overall model capabilities, highlighting the demand for methods that enable controllable bias reduction during inference. Activation steering is a popular approach for inference-time controllability that has shown potential in inducing safer behavior in large language models (LLMs). However, we observe that current steering methods struggle to correct biases, where equiprobable outcomes across demographic groups are required. To address this, we propose Direct Steering Optimization (DSO) which uses reinforcement learning to find linear transformations for steering activations, tailored to mitigate bias while maintaining control over model performance. We demonstrate that DSO achieves state-of-the-art trade-off between fairness and capabilities on both VLMs and LLMs, while offering practitioners inference-time control over the trade-off. Overall, our work highlights the benefit of designing steering strategies that are directly optimized to control model behavior, providing more effective bias intervention than methods that rely on pre-defined heuristics for controllability.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
