A Position Paper on the Automatic Generation of Machine Learning Leaderboards

TL;DR

This paper reviews the state of Automatic Leaderboard Generation in machine learning, proposing a unified framework, benchmarking guidelines, and discussing future challenges to improve automated leaderboard curation.

Contribution

It provides the first comprehensive overview of ALG research, introduces a standardized conceptual framework, and offers benchmarking guidelines to advance the field.

Findings

Identified fundamental differences in ALG approaches

Proposed a unified conceptual framework for ALG

Suggested benchmarking guidelines for fair evaluation

Abstract

An important task in machine learning (ML) research is comparing prior work, which is often performed via ML leaderboards: a tabular overview of experiments with comparable conditions (e.g., same task, dataset, and metric). However, the growing volume of literature creates challenges in creating and maintaining these leaderboards. To ease this burden, researchers have developed methods to extract leaderboard entries from research papers for automated leaderboard curation. Yet, prior work varies in problem framing, complicating comparisons and limiting real-world applicability. In this position paper, we present the first overview of Automatic Leaderboard Generation (ALG) research, identifying fundamental differences in assumptions, scope, and output formats. We propose an ALG unified conceptual framework to standardise how the ALG task is defined. We offer ALG benchmarking guidelines, including recommendations for datasets and metrics that promote fair, reproducible evaluation. Lastly, we outline challenges and new directions for ALG, such as, advocating for broader coverage by including all reported results and richer metadata.