Ellie Pavlick

Is This Just Fantasy? Language Model Representations Reflect Human Judgments of Event Plausibility

How Do Language Models Compose Functions?

Transferring Linear Features Across Language Models With Model Stitching

$100K or 100 Days: Trade-offs when Pre-Training with Academic Resources

Born a Transformer -- Always a Transformer? On the Effect of Pretraining on Architectural Abilities

The Same but Different: Structural Similarities and Differences in Multilingual Language Modeling

Dual Process Learning: Controlling Use of In-Context vs. In-Weights Strategies with Weight Forgetting

Transformer Mechanisms Mimic Frontostriatal Gating Operations When Trained on Human Working Memory Tasks