Interaction locality is introduced as a task-geometry-aware measurement framework showing that high-level states in recursive models write locally while recursive updates build broader structures on maze, Sudoku, ARC-AGI, and 3D grounding tasks.
Ivanitskiy et al
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Supervised fine-tuning lets LLMs linearly encode action validity and state predicates, with broader state-space coverage during training improving world-model recovery.
Language models encode modal categories via linear difference vectors in their activations that predict fine-grained human plausibility judgments better than prior reports suggested.
citing papers explorer
-
Interaction Locality in Hierarchical Recursive Reasoning
Interaction locality is introduced as a task-geometry-aware measurement framework showing that high-level states in recursive models write locally while recursive updates build broader structures on maze, Sudoku, ARC-AGI, and 3D grounding tasks.
-
A Close Look At World Model Recovery In Supervised Fine-Tuned LLM Planners
Supervised fine-tuning lets LLMs linearly encode action validity and state predicates, with broader state-space coverage during training improving world-model recovery.
-
Is This Just Fantasy? Language Model Representations Reflect Human Judgments of Event Plausibility
Language models encode modal categories via linear difference vectors in their activations that predict fine-grained human plausibility judgments better than prior reports suggested.