Search papers, labs, and topics across Lattice.
8 papers from Google Research on Constitutional AI & AI Ethics
Safety fine-tuning might inadvertently be stripping LLMs of their ability to understand non-human minds and entertain spiritual beliefs, even while preserving Theory of Mind.
Despite the effort required, Android developers overwhelmingly support platform-level changes to combat fingerprinting, suggesting a path to enhanced user privacy through collaborative platform-developer initiatives.
LLMs get *more* honest when they have time to reason, defying human tendencies and revealing surprising insights about their internal representational geometry.
LLMs are becoming "epistemic agents" that shape our knowledge environment, so we need a new framework for evaluating and governing them based on trustworthiness, not just performance.
Finally, a framework to quantify AI's cultural intelligence, moving beyond ad-hoc cultural benchmarks to a systematic, extensible, and theoretically grounded approach.
Forget prompt engineering: PCAS deterministically enforces complex authorization policies in multi-agent systems, boosting compliance from 48% to 93% without restructuring existing agents.
Natural privacy filters, despite their promise for tighter privacy accounting, aren't universally "free," limiting their applicability to specific families of differentially private mechanisms.
DPO's success isn't just clever engineering鈥攊t's deeply rooted in human choice theory, unlocking a surprisingly flexible framework for preference optimization and justifying many DPO extensions.
