Moritz Hardt

8

Papers

45

Total Citations

Papers (8)

Limits to scalable evaluation at the frontier: LLM as judge won’t beat twice the data

Unprocessing Seven Years of Algorithmic Fairness

How Benchmark Prediction from Fewer Data Misses the Mark

NeurIPS 2025arXiv

Causal Inference from Competing Treatments

Causal Inference out of Control: Estimating Performativity without Treatment Randomization

Allocation Requires Prediction Only if Inequality Is Low

Inherent Trade-Offs between Diversity and Stability in Multi-Task Benchmarks

Don’t Label Twice: Quantity Beats Quality when Comparing Binary Classifiers on a Budget