Yanai Elazar

OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens

arXiv 2025

OLMo: Accelerating the Science of Language Models

arXiv 2024

Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research

arXiv 2024

A Survey on Data Selection for Language Models

arXiv 2024

How Many Van Goghs Does It Take to Van Gogh? Finding the Imitation Threshold

arXiv 2024

Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback

arXiv 2024

What's In My Big Data?

arXiv 2023

Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation

arXiv 2023

Lexical Generalization Improves with Larger Models and Longer Training

arXiv 2022

Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection

null-it-out-guarding-protected-attributes-by-1

Hannaneh Hajishirzi

professor

Noah A. Smith

Dirk Groeneveld

Jesse Dodge

Luca Soldaini

Abhilasha Ravichander

Akshita Bhagia

Dustin Schwenk

Ian Magnusson

Nathan Lambert

researcher