|国家预印本平台
首页|What Does it Mean for a Neural Network to Learn a "World Model"?

What Does it Mean for a Neural Network to Learn a "World Model"?

What Does it Mean for a Neural Network to Learn a "World Model"?

来源:Arxiv_logoArxiv
英文摘要

We propose a set of precise criteria for saying a neural net learns and uses a "world model." The goal is to give an operational meaning to terms that are often used informally, in order to provide a common language for experimental investigation. We focus specifically on the idea of representing a latent "state space" of the world, leaving modeling the effect of actions to future work. Our definition is based on ideas from the linear probing literature, and formalizes the notion of a computation that factors through a representation of the data generation process. An essential addition to the definition is a set of conditions to check that such a "world model" is not a trivial consequence of the neural net's data or task.

Kenneth Li、Fernanda Viégas、Martin Wattenberg

计算技术、计算机技术

Kenneth Li,Fernanda Viégas,Martin Wattenberg.What Does it Mean for a Neural Network to Learn a "World Model"?[EB/OL].(2025-07-29)[2025-08-11].https://arxiv.org/abs/2507.21513.点此复制

评论