**LLM的概率信念更新并非始终符合贝叶斯原则**

_LLMs Are Not (Consistently) Bayesian: Quantifying Internal (In)consistencies of LLMs’ Probabilistic Beliefs_

> 苹果机器学习研究团队提出新方法,通过

**来源信息**
- **来源**:Apple Machine Learning Research(RSS)
- **分类**:论文
- **发布时间**:2026-08-28 08:00(北京时间)
- **原文**:[打开原文](https://machinelearning.apple.com/research/llms-not-consistently-bayesian)