Preprint
Aug 2026
What Does Prompt Learning Change? -A Natural-Language Concept Analysis of Vision-Language Models
This work presents PromptSpLiCE, a post-hoc method that expresses each class-conditioned text embedding as a sparse combination of concepts from a fixed natural-language dictionary, using the same dictionary before and after prompt learning to compare changes in their concept profiles.
Ryousuke Kamiya, Hiroshi Kera, Kazuhiko Kawamoto
· 0 citations