Research

AI/ML Evaluation and Benchmarking

Benchmark data repositories for better benchmarking
Rachel Longjohn*, Markelle Kelly*, Sameer Singh, and Padhraic Smyth.
NeurIPS (Datasets and Benchmarks), 2024.

Statistical uncertainty quantification for aggregate task-performance metrics in ML benchmarks
Rachel Longjohn*, Giri Gopalan*, and Emily Casleton.
NeurIPS Workshop on Statistical Frontiers in LLMs and Foundation Models, 2024.

Statistics/ML Methodology in Criminal Justice Applications

(Under review) Score-based Likelihood Ratios For Authorship Verification with Authorship Embeddings
Rachel Longjohn, Kai Nelson, and Padhraic Smyth.

Likelihood ratios for changepoints in categorical count data with applications in digital forensics
Rachel Longjohn and Padhraic Smyth.
Journal of Forensic Sciences, 2024.

Likelihood ratios for categorical count data with applications in digital forensics
Rachel Longjohn, Padhraic Smyth, and Hal S. Stern.
Law, Probability, and Risk, 2022.

Tutorial on Likelihood Ratios with Applications in Digital Forensics
Rachel Longjohn and Padhraic Smyth.
Center for Statistics and Applications in Forensic Evidence (CSAFE) Summer Webinar Series, 2022.