3 papers
cs.LO2026
LeanCat: A Benchmark Suite for Formal Category Theory in Lean (Part I: 1-Categories)
Rongge Xu, Hui Dai, Yiming Fu +5
While large language models (LLMs) have demonstrated impressive capabilities in formal theorem proving, current benchmarks fail to adequately measure library-grounded abstraction -…
cs.AI2026
Neuro-Symbolic Compliance: Integrating LLMs and SMT Solvers for Automated Financial Legal Analysis
Yung-Shen Hsia, Fang Yu, Jie-Hong Roland Jiang
Financial regulations are increasingly complex, hindering automated compliance-especially the maintenance of logical consistency with minimal human oversight. We introduce a Neuro-…
cs.LO2025
Model Counting for Dependency Quantified Boolean Formulas
Long-Hin Fung, Che Cheng, Jie-Hong Roland Jiang +2
Dependency Quantified Boolean Formulas (DQBF) generalize QBF by explicitly specifying which universal variables each existential variable depends on, instead of relying on a linear…