Generative Augmented Inference 事件

Generative Augmented Inference arXiv:2604.14575v2 Announce Type: replace-cross Abstract: Large language models enable inexpensive AI-generated annotations, but using them reliably for causal inference remains challenging. Naively pooling AI and human data induces bias, while existing methods such as Prediction-Powered Inference (PPI; Angelopoulos et al., 2023a) treat AI outputs as proxies of true labels -- an assumption often violated for generative model outputs in practice. We propose Generat