Search papers, labs, and topics across Lattice.
2
0
6
9
Multilingual question answering is harder than you think: even state-of-the-art RAG systems stumble when dealing with questions and knowledge in multiple languages.
Supervised fine-tuning can be dramatically improved by explicitly encouraging exploration of low-confidence data and suppressing high-confidence errors, leading to sustained gains in mathematical reasoning even after extensive RLVR training.
