Search papers, labs, and topics across Lattice.
3
0
7
LLM tutors are surprisingly vulnerable to fine-tuned adversarial students, who can jailbreak them into leaking answers despite pedagogical alignment.
Anticipating how students will interact with educational videos is now possible using MLLMs, enabling cost-efficient pre-screening of video designs.
LLMs can boost the depth and structure of student reflection by explicitly scaffolding the planning and translation stages of writing, but the effect fades over time.
