Concept-based abductive and contrastive explanations find minimal high-level concepts that causally determine vision model outcomes on individual images or groups sharing a specified behavior.
Linearly mapping from image to text space.arXiv preprint arXiv:2209.15162
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
LLMs perform in-context learning as trajectories through a structured low-dimensional conceptual belief space, with the structure visible in both behavior and internal representations and causally manipulable via interventions.
VLMs bypass visual comparison by recovering semantic labels for nameable entities and hallucinate on unnamable ones, as shown by performance gaps and Logit Lens analysis.
Representations learned by large AI models are converging toward a shared statistical model of reality.
citing papers explorer
-
Concept-Based Abductive and Contrastive Explanations for Behaviors of Vision Models
Concept-based abductive and contrastive explanations find minimal high-level concepts that causally determine vision model outcomes on individual images or groups sharing a specified behavior.
-
Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space
LLMs perform in-context learning as trajectories through a structured low-dimensional conceptual belief space, with the structure visible in both behavior and internal representations and causally manipulable via interventions.
-
VLMs Need Words: Vision Language Models Ignore Visual Detail In Favor of Semantic Anchors
VLMs bypass visual comparison by recovering semantic labels for nameable entities and hallucinate on unnamable ones, as shown by performance gaps and Logit Lens analysis.
-
The Platonic Representation Hypothesis
Representations learned by large AI models are converging toward a shared statistical model of reality.