Search papers, labs, and topics across Lattice.
University of Technology Nuremberg
4
0
6
7
Historical language change is not only multidimensional but also varies significantly in timing and direction across languages, challenging existing paradigms in linguistic research.
Annotation reporting in NLP is improving, but critical details that affect validity are still frequently overlooked, especially in model evaluations.
LLMs' temporal reasoning crumbles in low-resource languages and rarer calendar formats, not due to a lack of reasoning ability, but because poor tokenization fragments dates and times.
LLMs struggle to provide reliable answers to Islamic queries, but Fanar-Sadiq's multi-agent architecture, with specialized modules for scripture, jurisprudence, and calculations, delivers grounded and verifiable responses.
