Search papers, labs, and topics across Lattice.
3
1
5
5
ConRub-Med achieves unprecedented accuracy in open-ended medical question answering by leveraging scalable, model-generated rubrics that outperform traditional expert-driven methods.
Minimizing interpolation during data generation can significantly boost the effectiveness of imitation learning, yielding higher success rates in complex manipulation tasks.
Current LLMs still struggle with multi-turn medical diagnosis, needing more than just bigger models to truly master dialogue management.
