HiTZ zentroa
HiTZ is a reference center on Language Technologies. Its aim is to promote research, training, technological transfer and innovation in Artificial Intelligence.
Spain
Pinned Repositories
eustagger-lite
Eustagger Lite
GoLLIE
Guideline following Large Language Model for Information Extraction
latxa
Latxa: An Open Language Model and Evaluation Suite for Basque
lm-contamination
The LM Contamination Index is a manually created database of contamination evidences for LMs.
lm-evaluation-harness
A framework for few-shot evaluation of autoregressive language models.
MedExpQA
multilingual-abstrct
ses-lemma
Evaluating Shortest Edit Script Methods for Contextual Lemmatization
This-is-not-a-Dataset
We introduce a large semi-automatically generated dataset of ~400,000 descriptive sentences about commonsense knowledge that can be true or false in which negation is present in about 2/3 of the corpus in different forms that we use to evaluate LLMs
xnli-eu
XNLIeu: a dataset for cross-lingual NLI in Basque
HiTZ zentroa's Repositories
hitz-zentroa/GoLLIE
Guideline following Large Language Model for Information Extraction
hitz-zentroa/lm-contamination
The LM Contamination Index is a manually created database of contamination evidences for LMs.
hitz-zentroa/latxa
Latxa: An Open Language Model and Evaluation Suite for Basque
hitz-zentroa/This-is-not-a-Dataset
We introduce a large semi-automatically generated dataset of ~400,000 descriptive sentences about commonsense knowledge that can be true or false in which negation is present in about 2/3 of the corpus in different forms that we use to evaluate LLMs
hitz-zentroa/eustagger-lite
Eustagger Lite
hitz-zentroa/MedExpQA
hitz-zentroa/lm-evaluation-harness
A framework for few-shot evaluation of autoregressive language models.
hitz-zentroa/multilingual-abstrct
hitz-zentroa/ses-lemma
Evaluating Shortest Edit Script Methods for Contextual Lemmatization
hitz-zentroa/xnli-eu
XNLIeu: a dataset for cross-lingual NLI in Basque