Search papers, labs, and topics across Lattice.
ISP RAS Research Center for Trusted Artificial Intelligence, SB AI Lab
2
0
4
Medical LLMs do not need to trade diagnostic rigor for bedside manner: conditioning generation on inferred patient affect consistently beats neutral baselines on both human clarity ratings and objective clinical benchmarks.
Procedural memory boosts LLM performance in workplace tasks, with some skills achieving over 73% accuracy across different models while others falter under transfer.