Search papers, labs, and topics across Lattice.
University of Helsinki
3
0
4
LLMs exhibit significant disagreement with human experts due to identifiable issues, revealing critical gaps in their reliability for systematic review screening.
LLMs can accelerate the discovery of functional software tools, achieving 24 successful implementations from 83 identified tools with just 4 hours of human effort.
Claude Opus can generate REST API tests that uncover 28% more unique log templates than human-written tests, suggesting LLMs can surpass human intuition in exploring API runtime behavior.
