Search papers, labs, and topics across Lattice.
3
0
6
UML diagrams dominate LLM applications in software engineering, but critical gaps in behavioral modeling and evaluation practices could hinder progress.
RPO-PDT's innovative reverse-roleplay mechanism transforms unresolved student interactions into reusable tutoring strategies, enhancing adaptive learning support.
LLMs can be made significantly safer at inference time, without any retraining, by using RL to dynamically optimize prompts based on dialogue context.
