语料库驱动AI方法生成的选择题选项可能存在频率偏差，警惕其教育应用中的隐藏陷阱。
arXiv:2602.17377v2 Announce Type: replace Abstract: In recent years, corpus-driven AI methods, such as Large Language Models (LLMs), have seen widespr…
揭示AI个性化记忆如何扭曲情感推理：同一句话，不同用户画像可能激发出截然不同的情绪解读。
arXiv:2510.09905v2 Announce Type: replace-cross Abstract: When an AI assistant remembers that Sarah is a single mother working two jobs, does it inter…
多模态AI自我评估存在系统性偏差，一种新发现的“偏好崩溃”现象加剧了模型反馈循环中的错误。
arXiv:2606.16682v1 Announce Type: new Abstract: When AI agents use language models to evaluate their own outputs in a feedback loop, systematic biases…