Search papers, labs, and topics across Lattice.
University of South Florida
4
0
7
LLMs' susceptibility to invisible-character prompt injections that flip paper review scores reveals a critical vulnerability in their application to academic peer review.
LLM judges in healthcare show promise for scalable evaluation, but their reliability swings wildly across tasks, demanding careful design and validation before trusting their verdicts.
Predicting when drivers will engage or disengage driving automation requires more than just video鈥擟AN bus data and route context are key, and handover/takeover events exhibit distinct temporal dependencies.
LLMs write funnier jokes when conditioned on a simulated online community discussion, improving clarity and social appropriateness by a large margin.
