Search papers, labs, and topics across Lattice.
5
0
7
5
LLMs struggle to grasp unspoken beliefs, falling short of human-level understanding in recognizing and updating implicatures.
Existing unlearning methods may look effective, but they often miss the mark on precision, leaving sensitive data vulnerable to resurfacing attacks.
Language specialization in multilingual MoEs happens mostly in the final layers, suggesting a surprisingly simple recipe for parameter-efficient adaptation.
Forget expensive downstream evaluations: token-level statistics from expert-written solutions can reliably forecast LLM performance with 10,000x less compute.
Forget contrastive learning: LLM2Vec-Gen learns text embeddings by representing the *response* an LLM would generate, unlocking safety and reasoning abilities for embedding tasks.
