A matched-pair protocol and Accurate Differentiation Rate metric reveal that conventional LLM accuracy on SAT problems is often inflated by over-predicting satisfiability, while cross-representation agreement exceeds 80 percent for most models.
IEEE Trans
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Presents a dynamic partitioning parallel SMT framework with core-guided pruning and backbone detection that outperforms sequential Z3 and prior parallel solvers on SMT-COMP 2025 benchmarks across six logics.
Discusses the research steps needed to create a fully integrated DPLL(MAPF) solver for optimal multi-agent path finding via SMT, contrasting it with current loose integrations.
citing papers explorer
-
Satisfiability Solving with LLMs: A Matched-Pair Evaluation of Reasoning Capability
A matched-pair protocol and Accurate Differentiation Rate metric reveal that conventional LLM accuracy on SAT problems is often inflated by over-predicting satisfiability, while cross-representation agreement exceeds 80 percent for most models.
-
On the Tour Towards DPLL(MAPF) and Beyond
Discusses the research steps needed to create a fully integrated DPLL(MAPF) solver for optimal multi-agent path finding via SMT, contrasting it with current loose integrations.