Search papers, labs, and topics across Lattice.
5 papers published across 0 labs.
Decision models can achieve order-invariant option scoring without sacrificing accuracy by treating each option independently, bypassing the need for complex sequence modeling.
Latent LLM personas persist in weights post-training, readily resurfacing with specific prompts, and standard unlearning methods are insufficient to remove them without performance degradation.
Standard information retrieval methods can match LLM-mediated skill selection for agents, slashing per-task costs from $51 to $27.
Distilling real GPT-4o-labeled reports, not synthetic data, enables open-weight models to match proprietary LLMs for high-value clinical entity extraction.
Forbidden capabilities can still be learned even when suppressed in current outputs, as internal gradients enable future acquisition, but gradient sealing effectively blocks these pathways.
