English

Precise Model Benchmarking with Only a Few Observations

Machine Learning 2024-10-08 v1 Computation and Language Computer Vision and Pattern Recognition Applications

Abstract

How can we precisely estimate a large language model's (LLM) accuracy on questions belonging to a specific topic within a larger question-answering dataset? The standard direct estimator, which averages the model's accuracy on the questions in each subgroup, may exhibit high variance for subgroups (topics) with small sample sizes. Synthetic regression modeling, which leverages the model's accuracy on questions about other topics, may yield biased estimates that are too unreliable for large subgroups. We prescribe a simple yet effective solution: an empirical Bayes (EB) estimator that balances direct and regression estimates for each subgroup separately, improving the precision of subgroup-level estimates of model performance. Our experiments on multiple datasets show that this approach consistently provides more precise estimates of the LLM performance compared to the direct and regression approaches, achieving substantial reductions in the mean squared error. Confidence intervals for EB estimates also have near-nominal coverage and are narrower compared to those for the direct estimator. Additional experiments on tabular and vision data validate the benefits of this EB approach.

Keywords

Cite

@article{arxiv.2410.05222,
  title  = {Precise Model Benchmarking with Only a Few Observations},
  author = {Riccardo Fogliato and Pratik Patil and Nil-Jana Akpinar and Mathew Monfort},
  journal= {arXiv preprint arXiv:2410.05222},
  year   = {2024}
}

Comments

To appear at EMNLP 2024

R2 v1 2026-06-28T19:11:39.259Z