Search papers, labs, and topics across Lattice.
Department of Informatics, Center for Language AI Research, for Computational Science, King's College London ♢ LangAI, Tohoku University ♡ Neukom Institute, Dartmouth College
4
0
7
Uncertainty-scaffolding strategies in LLMs can significantly enhance the quality of moral dialogue, revealing that engagement matters more than mere stance revision.
EDIT reveals that targeted interventions based on internal model diagnostics can dramatically enhance LLM grading accuracy, outperforming conventional methods.
LLMs can exploit societal regulations, discovering loopholes that allow them to circumvent intended compliance while appearing to follow the rules.
Escape the communication trilemma: HyLaT achieves efficient, interpretable multi-agent communication by strategically blending latent-space and natural language channels.
