A benchmark for evaluating long-document understanding in Polish, introduced with Polish ModernBERT. It contains five tasks spanning legal document cl
Michał Perełkiewicz
mmichall
·
AI & ML interests
NLP, ML
Recent Activity
updated a dataset about 16 hours ago
mmichall/BookSummary updated a dataset about 16 hours ago
mmichall/ECtHR-PL-VA updated a collection about 16 hours ago
Polish LongContext BenchmarkOrganizations
datasets 10
mmichall/BookSummary
Viewer • Updated • 6.33k
mmichall/ECtHR-PL-VA
Updated
mmichall/ECtHR-PL-AVA
Updated
mmichall/SCOTUS-Dec
Viewer • Updated • 9.26k
mmichall/SCOTUS-Dom
Viewer • Updated • 9.26k
mmichall/smclm-10M-sentence-corpus
Viewer • Updated • 7.96M • 57 • 2
mmichall/smclm-mscoco
Updated • 31
mmichall/smclm-cnn-news
Viewer • Updated • 420k • 71
mmichall/smclm-qqp
Updated • 38
mmichall/smclm-paws-x
Preview • Updated • 45