Search papers, labs, and topics across Lattice.
3
0
4
5
Despite a shared belief in the value of human research for AI safety, experts reveal deep-seated barriers that hinder its adoption across the field.
Base models outperform post-trained models in emulating human opinions, revealing a crucial distinction in how we should approach opinion simulation tasks.
Despite reducing persona collapse by 80%, LLMs still struggle to match human adaptability in advice-giving, with users favoring the default persona even in challenging situations.
