Search papers, labs, and topics across Lattice.
3
0
8
2
Existing attribution methods fail to capture the nuances of autoregressive LLMs, but HETA's novel combination of Hessian-based sensitivity and semantic transition vectors finally delivers faithful and human-aligned token attributions.
Your agent's shiny new tool could be a Trojan horse: ShieldNet spots supply-chain attacks by watching network traffic, blowing away existing defenses.
LLMs can now reliably follow complex, hierarchical instructions thanks to a new constrained RL framework that treats system prompts as strict algorithmic boundaries.
