Combining Constraint Programming Reasoning with Large Language Model Predictions

Abstract

Constraint Programming (CP) and Machine Learning (ML) face challenges in text generation due to CP's struggle with implementing "meaning" and ML's difficulty with structural constraints. This paper proposes a solution by combining both approaches and embedding a Large Language Model (LLM) in CP. The LLM handles word generation and meaning, while CP manages structural constraints. This approach builds on On-the-fly Constraint Programming Search (OTFS), improving it using LLM-generated domains. Compared to Beam Search (BS), a standard NLP method, this combined approach (OTFS with LLM) is faster and produces better results, ensuring all constraints are satisfied. This fusion of CP and ML presents new possibilities for enhancing text generation under constraints