Metonymic Circuits for Abstract Concept Grounding in Vision Transformers

arXiv cs.AIOctober 7, 2026en

arXiv cs.AI

AI Global Wire

arXiv:2610.06928v1 Announce Type: new Abstract: We study how Vision Transformers ground abstract concepts (e.g., angry) when training data provide limited direct referential evidence. We hypothesize a metonymic grounding mechanism in which abstract predictions are driven by concrete, interpretable anchor concepts (e.g., fire) that bridge visual signals to abstract semantics. By applying Transcoders on CLIP and DINO vision encoders, we recover intermediate features that can be associated with semantic labels for more concrete concepts, and trace their contributions in circuits underlying abstract concept recognition. Experiments on a carefully curated icon dataset reveal structured metonymic

This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.

• Verktyg
• Forskning