Track new results across pure and applied mathematics.
Search papers, labs, and topics across Lattice.
Affiliation:
2
0
5
2
Hundreds of adversarial honesty targets are sufficient to teach LLMs to confess their hidden behaviors and resist pressure to lie, outperforming existing methods without sacrificing utility.
Continuously nudging LLM activations during generation can effectively correct misalignment without sacrificing coherence, offering a lightweight runtime defense against adversarial prompts and other triggers.