A Position Paper on the Automatic Generation of Machine Learning Leaderboards

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.12 These datasets can sometimes be divided into further subsets based on the size of the leaderboard.E.g., the ORKG-PwC and NLP-TDMS datasets filter out leaderboards with less than five entries.Datasets can also be divided into predefined subsets.E.g., the ORKG datasets include pre-defined splits that correspond to experimentation by Kabongo et al. (2024) 13 .