Search papers, labs, and topics across Lattice.
3
4
3
13
Local evaluations can surpass state-of-the-art models like GPT-5.5, offering a new standard for auditing educational content in real-time.
Current AI risk assessment practices are inadequate, revealing critical gaps that could jeopardize the safety of intelligent systems in a rapidly evolving regulatory environment.
A lightweight model fine-tuned on AIriskEval-edu-db2 can rival leading models in pedagogical risk detection, all while maintaining privacy in educational settings.
