URANIA:严格差分隐私(Differential Privacy, DP)约束下,对海量 LLM 聊天记录做“用例洞察/主题总结”的框架
论文Urania: Differentially Private Insights into AI Use提出 […]
URANIA:严格差分隐私(Differential Privacy, DP)约束下,对海量 LLM 聊天记录做“用例洞察/主题总结”的框架 Read More »
论文Urania: Differentially Private Insights into AI Use提出 […]
URANIA:严格差分隐私(Differential Privacy, DP)约束下,对海量 LLM 聊天记录做“用例洞察/主题总结”的框架 Read More »
论文Clio: Privacy-Preserving Insights into Real-World AI
Clio(Claude insights and observations):让AI助手把数百万对话归纳成可探索的聚合洞察 Read More »
论文Chain-of-Thought Is Not Explainability揭示了一个关于人工智能的重要误
Chain-of-Thought(思维链)≠ 可解释性(Explainability) Read More »
论文Harnessing the Universal Geometry of Embeddings提出了首个无
文本嵌入(text embeddings)可在不同向量空间之间转换。将转换后的嵌入输入至预训练的零样本反演模型,能还原出输入文本的关键信息 Read More »