智能AI None 通过将公平视为对称操作来检测和减轻偏差 06514v1 Announce Type: new Abstract: Machine learning systems deployed in high stakes socioeconomic settings routinely d bias with and 2026-06-08 Nishit Singh
智能AI None 不要看数字：VLM 中的视觉锚定偏差和分层表示 11218v1 Announce Type: new Abstract: Embedded numeric anchors on images systematically bias Vision-Language Model qualit bias quality are 2026-05-13 M. Shalankin
智能AI None 更多思考，更多偏差：推理模型中的长度驱动位置偏差 06672v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning and reasoning-tuned models such as DeepSeek-R1 are reasoning and bias 2026-05-11 Xiao Wang