Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up
sbordt 's Collections
train-once-answer-all
forgetting-contamination-benchmark-questions

forgetting-contamination-benchmark-questions

updated Sep 5

The 44.000 de-duplicated benchmark questions used in "How Much Can We Forget about Data Contamination?" (ICML 2025)

Upvote
-

  • sbordt/forgetting-contamination-winogrande

    Viewer • Updated Jun 23 • 7.99k • 8

  • sbordt/forgetting-contamination-mmlu

    Viewer • Updated Jun 23 • 9.59k • 16

  • sbordt/forgetting-contamination-boolq

    Viewer • Updated Jun 23 • 2.85k • 11

  • sbordt/forgetting-contamination-arc-easy

    Viewer • Updated Jun 23 • 2.61k • 11

  • sbordt/forgetting-contamination-piqa

    Viewer • Updated Jun 23 • 8.71k • 18

  • sbordt/forgetting-contamination-hellaswag

    Viewer • Updated Jun 23 • 8.61k • 9

  • sbordt/forgetting-contamination-social_i_qa

    Viewer • Updated Jun 23 • 3.64k • 14
Upvote
-
  • Collection guide
  • Browse collections
Company
TOS Privacy About Jobs
Website
Models Datasets Spaces Pricing Docs