Search papers, labs, and topics across Lattice.
2
12
3
10
HiRoute achieves high safety rates and reduces over-refusal in LLMs by dynamically routing prompts based on input risk, challenging the effectiveness of static prompt tuning approaches.
LLMs can move beyond simple refusals to actively guide vulnerable users towards safe outcomes, achieving state-of-the-art safety and robustness against jailbreaks.
