Search papers, labs, and topics across Lattice.
3
0
6
2
RiskChainBench introduces RiskChainBench, pairing 3,600 synthetic token-text restoration inputs from 600 source sessions with 600 corresponding human-labeled local web environments that produces a frozen, evidence-cited risk report without message-side semantics or domain-reputation cues.
LMs don't incrementally track entities through state changes like you'd expect, but instead use a surprisingly fragile "global suppression tag" to handle removals, leading to predictable failure modes.
Turns out, LLMs rely far more on raw code access than documentation when answering repository-level questions, challenging the assumption that documentation is the primary driver of code understanding.
