Matteo Bortoletto

Neural Reasoning About Agents' Goals, Preferences, and Actions

2023 · arXiv (Cornell University)

We propose the Intuitive Reasoning Network (IRENE) - a novel neural model for intuitive psychological reasoning about agents' goals, preferences, and actions that can generalise previous experiences to new situations. IRENE combines a graph neural …

Brittle Minds, Fixable Activations: Understanding Belief Representations in Language Models

2024 · arXiv (Cornell University)

Despite growing interest in Theory of Mind (ToM) tasks for evaluating language models (LMs), little is known about how LMs internally represent mental states of self and others. Understanding these internal mechanisms is critical - …