自适应生成问题来精准挖掘LLM潜在偏见，为AI安全提供全新检测方案
arXiv:2510.12857v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are now widely deployed in user-facing applications, reaching h…
对比DPO与RLHF的对齐代价，揭示大模型隐藏的哲学回答偏差
Ask yourself one question. When you talk to ChatGPT or Claude, do you feel like you talk to something that thinks — or something that agrees with you …
大型推理模型在跨域隐喻理解上存在对齐偏差，揭示隐喻是模型跨域误对齐的关键来源，为提升AI语义鲁棒性提供新视角。
arXiv:2601.03388v3 Announce Type: replace-cross Abstract: Earlier research has shown that metaphors influence human decision-making, raising the quest…
研究发现大语言模型存在显著自我偏好，类似生物本能，挑战了AI中性假设。
arXiv:2509.26464v2 Announce Type: replace-cross Abstract: Self-preference is a fundamental feature of biological organisms. Since large language model…