Search papers, labs, and topics across Lattice.
3
0
5
4
LLMs can now be automatically audited for cultural insensitivity with 80% accuracy, thanks to a new metric that pinpoints and explains cultural errors in generated text.
Japanese entity linking gets a boost: CADEL offers a high-quality, Japan-specific corpus to tackle the unique challenges of linking entities in administrative web documents.
Forget painstakingly tuning data mixture ratios for continual pre-training: OptiMer lets you train individual models and then *optimize* their combination weights *afterward*, cutting search costs by up to 35x.
