Counterexample Guided Inductive Synthesis Using Large Language Models and Satisfiability Solving

Generative large language models (LLMs) can follow human-provided instruction prompts and generate human-like responses. Apart from natural language responses, they have been found to be effective at generating formal artifacts such as code, plans, and logical specifications. Despite their remarkably improved accuracy, these models are still known to produce factually incorrect or contextually inappropriate results despite their syntactic coherence - a phenomenon often referred to as hallucinations. This limitation makes it difficult to use these models to synthesize formal artifacts used in safety-critical applications. Unlike tasks such as text summarization and question-answering, bugs in code, plan, and other formal artifacts produced by LLMs can be catastrophic. We posit that we can use the satisfiability modulo theory (SMT) solvers as deductive reasoning engines to analyze the generated solutions from the LLMs, produce counterexamples when the solutions are incorrect, and provide that feedback to the LLMs exploiting the dialog capability of LLMs. This interaction between inductive LLMs and deductive SMT solvers can iteratively steer the LLM to generate the correct response. In our experiments, we use planning over the domain of blocks as our synthesis task for evaluating our approach. We use GPT-4, GPT3.5 Turbo, Davinci, Curie, Babbage, and Ada as the LLMs and Z3 as the SMT solver. Our method allows the user to communicate the planning problem in natural language; even the formulation of queries to SMT solvers is automatically generated from natural language. Thus, the proposed technique can enable non-expert users to describe their problems in natural language, and the combination of LLMs and SMT solvers can produce provably correct solutions.