Search papers, labs, and topics across Lattice.
3
6
5
Achieving human-level marking consistency, this LLM-as-Judge pipeline enhances educational assessments by grounding AI evaluations in official curriculum standards.
BioWeave enables smaller models to achieve reasoning performance on par with state-of-the-art LLMs, revolutionizing the landscape of biomedical question answering.
A global consensus on AI safety risks and capabilities has emerged from a panel of 100+ independent experts, representing a landmark effort in international collaboration.
