Search papers, labs, and topics across Lattice.
University of Illinois Urbana-Champaign
2
0
6
4
LLMs can ace prediction tasks in causal environments, but still fail to grasp the underlying causal mechanisms, revealing a critical blind spot in their reasoning abilities.
LLMs can be detoxified with minimal performance impact by surgically intervening on a small subset of attention heads causally linked to toxicity, identified via a novel causal inference approach.
