Search papers, labs, and topics across Lattice.
4
0
6
5
Reranking documents by language coherence can dramatically improve retrieval performance, as shown by LAMAR's superior results across multiple languages.
Answer-conditioning can undermine reasoning accuracy in LLMs, leading to a staggering 27-point drop on difficult tasks.
ACOER reduces token generation by over 60% while boosting accuracy, solving the reward collapse problem that plagues traditional efficiency training methods.
Low-resource languages can get a 15% boost in cross-lingual retrieval accuracy by using English as a Rosetta Stone during training.
