conftrace_

subpopulation performance

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

balanced performance (1) capability diversity (1) disaggregated evaluation (1) fairness regularizer (1) predictive model evaluation (1) gaussian mean estimation (1) simultaneous estimation (1) stein unbiased risk estimate (1) model-based metrics (1) influence score (1)

Papers

Robust Learning from Noisily Labeled Long-Tailed Data via Fairness Regularizer AAAI 2026 Improving Influence-based Instruction Tuning Data Selection for Balanced Learning of Diverse Capabilities EMNLP 2025 SureMap: Simultaneous mean estimation for single-task and multi-task disaggregated evaluation NeurIPS 2024 Model-based metrics: Sample-efficient estimates of predictive model subpopulation performance MLHC 2021