Search papers, labs, and topics across Lattice.
3
0
6
Context-Fractured Decomposition attacks expose a critical vulnerability in LLM agents, where harmless actions can lead to harmful outcomes through fragmented artifact interactions.
Existing hallucination detection methods are missing subtle, word-level medical errors, but a new data-centric pipeline and detector closes the gap by 15%.
RAG systems can now achieve 8x better PII leakage protection without sacrificing utility or speed, thanks to a novel "Verify-then-Route" paradigm.
