Emma Strubell

Holistically Evaluating the Environmental Impact of Creating Language Models

What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions

Large-Scale Training Data Attribution with Efficient Influence Functions

Hardware Scaling Trends and Diminishing Returns in Large-Scale Distributed Training

Source-Aware Training Enables Knowledge Attribution in Language Models

Generate to Discriminate: Expert Routing for Continual Learning

Efficiency Pentathlon: A Standardized Benchmark for Efficiency Evaluation