SOURCE-LINKED INTELLIGENCE

Beliefs and Behavior in Language Models

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

There is significant uncertainty about whether abstractions like beliefs or desires usefully describe the behavior of large language models (LLMs). In addition to the inherent scientific interest of this question, these latent quantities are often invoked to explain the behavior of LLMs to users or to define and evaluate harmful behaviors which are relative to intent. Nevertheless, we currently lack a means to systematically test whether concepts like "belief" are well-applied to LLMs, and hence whether they are likely to be fruitful ingredients of attempts to align models with human interests

Read original source ↗ Open in workspace

recordType

paper

region

Global