Hanna Hajishirzi

6 papers University of Washington/AI2

• Critical Batch Size Revisited: A Simple Empirical Approach to Large-Batch Language Model Training
• FlexOLMo: Open Language Models for Flexible Data Use
• Generalizing Verifiable Instruction Following
• OMEGA: Can LLMs Reason Outside the Box in Math? Evaluating Exploratory, Compositional, and Transformative Generalization
• SciArena: An Open Evaluation Platform for Non-Verifiable Scientific Literature-Grounded Tasks
• Signal and Noise: A Framework for Reducing Uncertainty in Language Model Evaluation