This work introduces a comprehensive framework for identifying dataset errors using a novel error annotation protocol and creates MMLU-Redux, which is a subset of 5,700 manually re-annotated questions across all 57 MMLU subjects.
Maybe not. We identify and analyse errors in the popular Massive Multitask Language Understanding (MMLU) benchmark. Even though MMLU is widely adopted, our analysis demonstrates numerous ground truth errors that obscure the true capabilities of LLMs. For example, we find that 57% of the analysed questions in the Virology subset contain errors. To address this issue, we introduce a comprehensive framework for identifying dataset errors using a novel error annotation protocol. Then, we create MMLU-Redux, which is a subset of 5,700 manually re-annotated questions across all 57 MMLU subjects. We estimate that 6.49% of MMLU questions contain errors. Using MMLU-Redux, we demonstrate significant discrepancies with the model performance metrics that were originally reported. Our results strongly advocate for revising MMLU's error-ridden questions to enhance its future utility and reliability as a benchmark. https://huggingface.co/datasets/edinburgh-dawg/mmlu-redux-2.0.
Joshua Ong Jun Leang
1 papers
Giwon Hong
1 papers
Alessio Devoto
1 papers
Alberto Carlo Maria Mancino
1 papers
Xuanli He
1 papers
Yu Zhao
1 papers
Xiaotang Du
1 papers
Mohammad Reza Ghasemi Madani
1 papers
Claire Barale
1 papers
R. McHardy
1 papers
Joshua Harris
1 papers
Emile van Krieken
1 papers
Pasquale Minervini
1 papers