Search papers, labs, and topics across Lattice.
3
0
7
8
A 32B model in Marathi performs like a 10B model in English, revealing how model size and reasoning can bridge language resource gaps in cross-lingual transfer.
Parser-derived supervision can replace costly human annotations, achieving up to 93.8% parse success in Danish and 80% preference in native speaker comparisons.
Trustworthiness in AI-generated responses is often overlooked, yet this study reveals that web search can lead to a staggering 35% of answers citing unreliable sources.
