Search papers, labs, and topics across Lattice.
3
0
7
2
This work introduces PACT (Pressure-Applied Compliance Testing), a benchmark for rule-following under pressure in AI agents assisting employees in daily tasks across twelve regulated enterprise domains and forty-eight scenarios, each set in a realistic multi-turn conversation.
Transformers encode an inferred partner's expertise early in the network, but interventions at peak decodability produce virtually zero downstream effect until patched past the midpoint.
Up to 50.2% of unauthorized requests can be falsely authorized by LLM memory, with executors blindly acting on these permissions 98.6% of the time.
