Search papers, labs, and topics across Lattice.
Affiliation:
4
0
6
Legal LLMs trained on surface features like citation count and legalese density learn to strategically withhold answers, becoming maximally "lawyerly" but minimally useful.
Higher offline conservatism in training can paradoxically increase vulnerability to reward hacking during online adaptation, challenging long-held assumptions in the field.
Interpolating between opposing directorial personas not only reveals surprising coherence improvements but also uncovers a shared moral-tone substrate in transformer models.
Systematic gaps in AI evaluation reporting are exposed, revealing inconsistencies that hinder reliable comparisons across thousands of models and benchmarks.
