From Crowdsourced Data to High-quality Benchmarks: Arena-Hard and Benchbuilder Pipeline

Tianle Li, Wei-Lin Chiang, Evan Frick, Lisa Dunlap, Tianhao Wu 0002, Banghua Zhu, Joseph E. Gonzalez, Ion Stoica. From Crowdsourced Data to High-quality Benchmarks: Arena-Hard and Benchbuilder Pipeline. In Forty-second International Conference on Machine Learning, ICML 2025, Vancouver, BC, Canada, July 13-19, 2025. OpenReview.net, 2025. [doi]

Abstract

Abstract is missing.