Larger LLMs acquire basic situation modeling before mentalizing on false-belief tasks, with performance depending on size, training volume, and post-training, yet remaining sensitive to non-factive verbs and agent knowledge states.
Toward a theory of generalizability in llm mechanistic interpretability research.arXiv preprint arXiv:2509.22831,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Humans and LLMs exhibit similar error patterns in common-sense reasoning, consistent with shared pattern-matching mechanisms rather than abstract world models.
citing papers explorer
-
Developmental Trajectories of Situation Modeling and Mentalizing in Transformer Language Models
Larger LLMs acquire basic situation modeling before mentalizing on false-belief tasks, with performance depending on size, training volume, and post-training, yet remaining sensitive to non-factive verbs and agent knowledge states.
-
Reasoning as Pattern Matching: Shared Mechanisms in Human and LLM Everyday Reasoning
Humans and LLMs exhibit similar error patterns in common-sense reasoning, consistent with shared pattern-matching mechanisms rather than abstract world models.