Search papers, labs, and topics across Lattice.
University of Florida Gainesville
2
0
3
LLMs' reasoning chains are surprisingly fragile at logical connectives, but targeted interventions at these "forking points" can dramatically improve accuracy more efficiently than brute-force methods.
LLMs can be steered to better logical reasoning by exploiting a shared, low-dimensional "logical subspace" learned by aligning natural language and symbolic reasoning views.
