Colin Raffel

Efficiently Estimating Data Efficiency for Language Model Fine-tuning

TokSuite: Measuring the Impact of Tokenizer Choice on Language Model Behavior

FineWeb2: One Pipeline to Scale Them All — Adapting Pre-Training Data Processing to Every Language

Enhancing Training Data Attribution with Representational Optimization

SmolLM2: When Smol Goes Big — Data-Centric Training of a Fully Open Small Language Model

Fishers for Free? Approximating the Fisher Information Matrix by Recycling the Squared Gradient Accumulator

AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution

The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions

Realistic Evaluation of Model Merging for Compositional Generalization