Language Models as Agent Models

Understand

Language models (LMs) are trained on collections of documents, written by individual human agents to achieve specific goals in an outside world.

• During training, LMs have access only to text of these documents, with no direct evidence of the internal states of the agents that produced them -- a fact often used to argue that LMs are incapable of modeling goal-directed aspects of human language production and comprehension.
• Can LMs trained on text learn anything at all about the relationship between language and use? I argue that LMs are models of intentional communication in a specific, narrow sense.
• When performing next word prediction given a textual context, an LM can infer and represent properties of an agent likely to have produced that context.