On the Workflows and Smells of Leaderboard Operations (LBOps): An Exploratory Study of Foundation Model Leaderboards

TL;DR

This study explores the workflows and common issues in foundation model leaderboards, proposing improvements to enhance transparency, accountability, and collaboration in model evaluation practices.

Contribution

It systematically analyzes real-world leaderboard operations, identifies workflow patterns, and uncovers eight types of leaderboard smells to improve FM evaluation transparency.

Findings

Identified five distinct leaderboard workflow patterns.

Developed a domain model capturing key components of LBOps.

Discovered eight types of leaderboard smells affecting transparency.

Abstract

Foundation models (FM), such as large language models (LLMs), which are large-scale machine learning (ML) models, have demonstrated remarkable adaptability in various downstream software engineering (SE) tasks, such as code completion, code understanding, and software development. As a result, FM leaderboards have become essential tools for SE teams to compare and select the best third-party FMs for their specific products and purposes. However, the lack of standardized guidelines for FM evaluation and comparison threatens the transparency of FM leaderboards and limits stakeholders' ability to perform effective FM selection. As a first step towards addressing this challenge, our research focuses on understanding how these FM leaderboards operate in real-world scenarios ("leaderboard operations") and identifying potential pitfalls and areas for improvement ("leaderboard smells"). In this regard, we collect up to 1,045 FM leaderboards from five different sources: GitHub, Hugging Face Spaces, Papers With Code, spreadsheet and independent platform, to examine their documentation and engage in direct communication with leaderboard operators to understand their workflows. Through card sorting and negotiated agreement, we identify five distinct workflow patterns and develop a domain model that captures the key components and their interactions within these workflows. We then identify eight unique types of leaderboard smells in LBOps. By mitigating these smells, SE teams can improve transparency, accountability, and collaboration in current LBOps practices, fostering a more robust and responsible ecosystem for FM comparison and selection.