Search papers, labs, and topics across Lattice.
3
0
6
8
Multimodal unlearning could revolutionize how we handle sensitive data in AI, enabling targeted removal without sacrificing model performance.
Agentic harnesses can significantly enhance LLM performance on deontic reasoning tasks, but not without introducing risks of degradation in numerical accuracy.
LLMs struggle to navigate the nuances of real-world rules, achieving only ~45% accuracy on a new benchmark of legal and policy reasoning tasks.
