Spurlens: finding spurious correlations in Multimodal llms

Best AI papers explained - Podcast készítő Enoch H. Kang

Podcast artwork

Kategóriák:

MLLMs exploit spurious correlations, affecting robustness and generalization The paper introduces SpurLens to identify and measure spurious cuesVarious prompting strategies were tested but none were effective 

Visit the podcast's native language site