Search papers, labs, and topics across Lattice.
MOE Key Laboratory of Computational Linguistics, Peking University, School of Computer Science, Peking University, Beijing Academy of Artificial Intelligence, Beijing, China
3
0
4
0
Steering signals are most effective when derived from execution-boundary states, not just from the presence of desired behaviors in the source text.
Current LLMs fail to effectively anticipate user needs, with even the latest models only succeeding in 26.7% of proactive scenarios.
Current LLMs achieve only 50.64% accuracy on a new benchmark for higher-order logical reasoning, revealing a critical gap in their reasoning capabilities.
