Using Large Language Models to Improve Query-based Constraint Acquisition
Using Large Language Models to Improve Query-based Constraint Acquisition
Younes Mechqrane, Christian Bessiere, Ismail Elabbassi
Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence
Main Track. Pages 1916-1925.
https://doi.org/10.24963/ijcai.2024/212
Most active constraint acquisition systems suffer from two weaknesses. They require the explicit generation of the set of potential constraints (the bias), whose size can be prohibitive for practical use of these systems, and the answers to queries contain little information. In this paper, we introduce ACQNOGOODS, an active learning schema that does not require the construction of a bias. We then propose LLMACQ, an active learning system that incorporates a Large Language Model component in the ACQNOGOODS schema. LLMACQ interprets the user’s answers given in natural language, leading to more informative communication. As our experiments show, the non requirement of a bias in extension combined to the higher level communication with the user allow LLMACQ to learn constraints of any arity and to dramatically decrease the number of queries.
Keywords:
Constraint Satisfaction and Optimization: CSO: Constraint learning and acquisition