Search papers, labs, and topics across Lattice.
3
0
6
4
Selective state-space adaptation can boost reasoning accuracy in language models by over 18% on challenging tasks, revealing the power of dynamic context management.
LLMs' math skills are more fragile than we thought: emotional language alone can throw off their reasoning by up to 10%.
LLMs' attention patterns subtly shift with emotional tone, and explicitly accounting for these shifts during training improves reading comprehension even on neutral datasets.
