Timezone: »

Active Learning Helps Pretrained Models Learn the Intended Task
Alex Tamkin · Dat Nguyen · Salil Deshpande · Jesse Mu · Noah Goodman

Wed Nov 30 02:00 PM -- 04:00 PM (PST) @ Hall J #107

Models can fail in unpredictable ways during deployment due to task ambiguity, when multiple behaviors are consistent with the provided training data. An example is an object classifier trained on red squares and blue circles: when encountering blue squares, the intended behavior is undefined. We investigate whether pretrained models are better active learners, capable of disambiguating between the possible tasks a user may be trying to specify. Intriguingly, we find that better active learning is an emergent property of the pretraining process: pretrained models require up to 5 times fewer labels when using uncertainty-based active learning, while non-pretrained models see no or even negative benefit. We find these gains come from an ability to select examples with attributes that disambiguate the intended behavior, such as rare product categories or atypical backgrounds. These attributes are far more linearly separable in pretrained model's representation spaces vs non-pretrained models, suggesting a possible mechanism for this behavior.

Author Information

Alex Tamkin (Stanford University)
Dat Nguyen
Salil Deshpande (Stanford University)
Jesse Mu (Stanford University)
Noah Goodman (Stanford University)

More from the Same Authors