arXiv preprint / 6D位姿

Can LLMs Detect Their Confabulations? Estimating Reliability in Uncertainty-Aware Language Models

作者：Sweden tzho@kth.se &Johanne Medina QCRI, HBKU Doha, Qatar jomedina@hbku.edu.qa &Sanjay Chawla QCRI, Qatar schawla@hbku.edu.qa · 单位：KTH Royal Institute of Technology · 会议/期刊：arXiv preprint · 方向：6D位姿 · 发布日期：2025-08-11

6D位姿估计
新标签打开 AlphaXiv新标签打开 Code
Can LLMs Detect Their Confabulations? Estimating Reliability in Uncertainty-Aware Language Models figure
AlphaXiv 中文概览（可滚动查看）