What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models
This addresses the challenge of assessing the true understanding of foundation models for researchers and practitioners, but it is incremental as it builds on existing evaluation methods.
The paper tackles the problem of evaluating whether foundation models capture deeper world understanding by developing an inductive bias probe technique, finding that models often excel at training tasks but fail to develop inductive biases aligned with underlying world models, such as consistently failing to apply Newtonian mechanics in new physics tasks.
Foundation models are premised on the idea that sequence prediction can uncover deeper domain understanding, much like how Kepler's predictions of planetary motion later led to the discovery of Newtonian mechanics. However, evaluating whether these models truly capture deeper structure remains a challenge. We develop a technique for evaluating foundation models that examines how they adapt to synthetic datasets generated from some postulated world model. Our technique measures whether the foundation model's inductive bias aligns with the world model, and so we refer to it as an inductive bias probe. Across multiple domains, we find that foundation models can excel at their training tasks yet fail to develop inductive biases towards the underlying world model when adapted to new tasks. We particularly find that foundation models trained on orbital trajectories consistently fail to apply Newtonian mechanics when adapted to new physics tasks. Further analysis reveals that these models behave as if they develop task-specific heuristics that fail to generalize.