Search papers, labs, and topics across Lattice.
5
0
10
Activations, not just descriptions, unlock the prediction of how LLM alignment generalizes to unseen values, revealing a structured value space.
Fine-tuning on poetry boosts idiom comprehension in LLMs, but cultural fine-tuning paradoxically undermines proverb interpretation accuracy.
Proprietary MLLMs may achieve high diagnostic accuracy, but they still struggle with reliable clinical reasoning, revealing significant gaps in their practical utility.
PaperMentor delivers actionable writing feedback that 90.6% of users found useful, setting a new standard for AI-assisted manuscript development.
Language models leak personal data at an alarming rate, with even small models verbatim parroting almost 3% of personal information instances.
