2 papers
cs.CL2026
Crowdsourcing Piedmontese to Test LLMs on Non-Standard Orthography
Gianluca Vico, JindÅich Libovický
We present a crowdsourced dataset for Piedmontese, an endangered Romance language of northwestern Italy. The dataset comprises 145 Italian-Piedmontese parallel sentences derived fr…
cs.CL2026
CUS-QA: Local-Knowledge-Oriented Open-Ended Question Answering Dataset
JindÅich Libovický, JindÅich Helcl, Andrei Manea +1
We introduce CUS-QA, a benchmark for evaluation of open-ended regional question answering that encompasses both textual and visual modalities. We also provide strong baselines usin…