Search papers, labs, and topics across Lattice.
University of Georgia
3
6
4
8
LLMs exhibit Pareto-like tradeoffs in medical diagnosis, where neutralizing user prompts to improve plausibility and conciseness can simultaneously reduce coverage of critical conditions.
Your agent's shiny new tool could be a Trojan horse: ShieldNet spots supply-chain attacks by watching network traffic, blowing away existing defenses.
Despite claims of safety alignment, state-of-the-art LLMs still spill the beans on hazardous scientific knowledge at an alarming rate, failing nearly 80% of the time on a new regulation-grounded benchmark.
