Maintaining MTEB: Towards Long Term Usability and Reproducibility of Embedding Benchmarks
This work addresses the problem of benchmark sustainability for researchers and practitioners in machine learning, but it is incremental as it builds on existing MTEB methodology.
The paper tackles the challenge of ensuring long-term usability and reproducibility for the Massive Text Embedding Benchmark (MTEB) by focusing on engineering aspects like continuous integration pipelines, dataset validation, and community contributions, resulting in a more comprehensive and maintainable benchmark.
The Massive Text Embedding Benchmark (MTEB) has become a standard evaluation platform for text embedding models. While previous work has established the core benchmark methodology, this paper focuses on the engineering aspects that ensure MTEB's continued reproducibility and extensibility. We present our approach to maintaining robust continuous integration pipelines that validate dataset integrity, automate test execution, and assess benchmark results' generalizability. We detail the design choices that collectively enhance reproducibility and usability. Furthermore, we discuss our strategies for handling community contributions and extending the benchmark with new tasks and datasets. These engineering practices have been instrumental in scaling MTEB to become more comprehensive while maintaining quality and, ultimately, relevance to the field. Our experiences offer valuable insights for benchmark maintainers facing similar challenges in ensuring reproducibility and usability in machine learning evaluation frameworks. The MTEB repository is available at: https://github.com/embeddings-benchmark/mteb