Search papers, labs, and topics across Lattice.
TU Wien Vienna, AustriaUniversity of Klagenfurt Klagenfurt, Austria
3
0
6
LLMs can automatically discover constraints that dramatically accelerate Answer Set Programming solvers, achieving up to 5x speedups on standard benchmarks.
Human-AI collaboration using LLMs and symbolic solvers just cracked a notoriously hard problem in combinatorial design theory, finding a tight lower bound on Latin square imbalance.
LLM self-explanations are more sensitive to semantic framing than actual task performance, suggesting they reflect semantic expectations rather than true internal states.
