Search papers, labs, and topics across Lattice.
4
0
5
46
Existing explainability methods misrepresent multimodal decision-making, often conflating genuine reasoning with shallow shortcuts.
LLMs can be six times more biased when demographic identity is conveyed implicitly through cultural cues, even when explicit biases are suppressed.
Even the best MLLMs still fall far short of human performance in collaborative spatial reasoning, revealing a critical gap in their ability to build and maintain shared mental models through dialogue.
Forget scaling laws: the *structure* of your AI governance system matters more than the specific LLM when it comes to preventing corruption.
