Recommendations and Reporting Checklist for Rigorous & Transparent Human Baselines in Model Evaluations

TL;DR

This paper emphasizes the need for more rigorous and transparent human baselines in foundation model evaluations, providing a checklist to improve measurement and reporting practices for better comparison between human and AI performance.

Contribution

It offers a comprehensive framework and checklist for designing, executing, and reporting human baselines, addressing current shortcomings in AI evaluation practices.

Findings

Identified gaps in existing human baselining methods

Developed a systematic checklist for better reporting

Reviewed 115 studies to assess baseline quality

Abstract

In this position paper, we argue that human baselines in foundation model evaluations must be more rigorous and more transparent to enable meaningful comparisons of human vs. AI performance, and we provide recommendations and a reporting checklist towards this end. Human performance baselines are vital for the machine learning community, downstream users, and policymakers to interpret AI evaluations. Models are often claimed to achieve "super-human" performance, but existing baselining methods are neither sufficiently rigorous nor sufficiently well-documented to robustly measure and assess performance differences. Based on a meta-review of the measurement theory and AI evaluation literatures, we derive a framework with recommendations for designing, executing, and reporting human baselines. We synthesize our recommendations into a checklist that we use to systematically review 115 human baselines (studies) in foundation model evaluations and thus identify shortcomings in existing baselining methods; our checklist can also assist researchers in conducting human baselines and reporting results. We hope our work can advance more rigorous AI evaluation practices that can better serve both the research community and policymakers. Data is available at: https://github.com/kevinlwei/human-baselines