paper-with-me

홈 › Papers

Prediction-Powered Smoothing and Validation for Disaggregated AI Evaluation

2026-09-17 · Sho Kawano, Zehang Richard Li, Paul A. Parker hf

Evaluating an AI system requires disaggregated assessment, as performance varies across domains such as benchmark task types or conversation types in deployed agents. Exhaustive testing is expensive, so evaluation rests on a sample of labeled units. We treat the evaluation set as a finite population and seek accurate point and interval estimates of each domain mean. Direct estimators, including prediction-powered inference (PPI), use only a domain's own labels and are imprecise where labels are few. Small area estimation addresses this problem, and we build on it to develop an integrated workflow for estimation and validation. For estimation, we propose prediction-powered smoothing (PP-S), a Bayesian model fit to each domain's prediction-powered estimate, with an extension that borrows strength across a reporting taxonomy (PP-TS). For validation, we derive a new, approximately unbiased design-based cross-validation score for choosing among direct and smoothed estimators. We study a curated benchmark with verifiable grading and deployed agent traffic graded by humans, each with every outcome observed. In both, the proposed estimators improve on the direct estimators in point and interval estimation, with near-nominal coverage. At the same sampling budget, our score selects as well as an independent validation sample does and estimates the selected estimator's error far more accurately.

📄 PDF Abstract BibTeX arXiv:2609.20758

Code (1)

InsomaniacElf/sg-tamil-tts-resources- ★ 1

Similar Papers 제목 키워드 기반

SureMap: Simultaneous Mean Estimation for Single-Task and Multi-Task Disaggregated Evaluation

2024-11-14 · Mikhail Khodak, Lester Mackey, Alexandra Chouldechova, Miroslav Dudík

Disaggregated evaluation -- estimation of performance of a machine learning model on different subpopulations -- is a core task when assessing performance and group-fairness of AI systems. A key challenge is that evaluat…

Fairness

Frontier: Towards Comprehensive and Accurate LLM Inference Simulation

2026-05-20 · Yicheng Feng, Xin Tan, Yangtao Deng, Yimin Jiang 외 arxiv

Modern LLM serving is no longer homogeneous or monolithic. Production systems now combine disaggregated execution, complex parallelism, runtime optimizations, and stateful workloads such as reasoning, agents, and RL roll…

Understanding challenges to the interpretation of disaggregated evaluations of algorithmic fairness

2025-06-04 · Stephen R. Pfohl, Natalie Harris, Chirag Nagpal, David Madras 외

Disaggregated evaluation across subgroups is critical for assessing the fairness of machine learning models, but its uncritical use can mislead practitioners. We show that equal performance across subgroups is an unrelia…

FairnessSelection bias

Designing Disaggregated Evaluations of AI Systems: Choices, Considerations, and Tradeoffs

2021-03-10 · Solon Barocas, Anhong Guo, Ece Kamar, Jacquelyn Krones 외

Disaggregated evaluations of AI systems, in which system performance is assessed and reported separately for different groups of people, are conceptually simple. However, their design involves a variety of choices. Some …

Forecasting CPI Inflation Components with Hierarchical Recurrent Neural Networks

2020-11-16 · Oren Barkan, Jonathan Benchimol, Itamar Caspi, Eliya Cohen 외

We present a hierarchical architecture based on Recurrent Neural Networks (RNNs) for predicting disaggregated inflation components of the Consumer Price Index (CPI). While the majority of existing research is focused mai…