Search papers, labs, and topics across Lattice.
2
0
6
1
K-EXAONE 2.0 achieves over three times the capacity of its predecessor while enhancing multilingual capabilities and long-context reasoning.
LLMs still struggle with questions containing negative constraints, but a new framework leveraging Python-formatted logical forms and self-directed refinement significantly improves performance on this neglected but common real-world KGQA task.
