Structural certification maps bounded goal-conditioned performance to O(1/n) + O(δ) entry-wise error bounds on an agent's internal world model for transitions filtered by deep compositional goals.
Can language models encode perceptual structure without grounding? a case study in color
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
LLM personas exhibit model-dependent personality effects on color choices and context-driven chart preferences, limiting their use as direct substitutes for human participants in visualization design.
Introduces 9 synthetic annotation tasks and benchmarks for behavioral cloning, finding hierarchical skill learning, scaling benefits, effective multi-task pretraining, and shared internal representations of task phases and mistakes.
Representations learned by large AI models are converging toward a shared statistical model of reality.
Perceptual geometry for color, pitch, emotion and taste emerges transiently in intermediate layers of transformer LLMs despite purely textual training.
citing papers explorer
-
World Models in Pieces: Structural Certification for General Agents
Structural certification maps bounded goal-conditioned performance to O(1/n) + O(δ) entry-wise error bounds on an agent's internal world model for transitions filtered by deep compositional goals.
-
When Do LLM Personas Support Visualization Design? A Cross-Model Study of Color Assignment and Chart Choice
LLM personas exhibit model-dependent personality effects on color choices and context-driven chart preferences, limiting their use as direct substitutes for human participants in visualization design.
-
A Systematic Study of Behavioral Cloning for Scientific Data Annotation
Introduces 9 synthetic annotation tasks and benchmarks for behavioral cloning, finding hierarchical skill learning, scaling benefits, effective multi-task pretraining, and shared internal representations of task phases and mistakes.
-
The Platonic Representation Hypothesis
Representations learned by large AI models are converging toward a shared statistical model of reality.
-
Geometry of Human Perceptual Domains Emerges Transiently in LLM Representations
Perceptual geometry for color, pitch, emotion and taste emerges transiently in intermediate layers of transformer LLMs despite purely textual training.