Abstract
Constraint Satisfaction Problems (CSPs) are a core technology that solves many real-world problems, especially for configuration tasks. A key success factor in this context is an efficient knowledge acquisition process where domain experts and knowledge engineers (developers of CSPs) should develop an agreement on the correctness of the expanding knowledge base as soon as possible. In this paper, we show how large language models (LLMs) can be applied to the automated generation of solutions for constraint satisfaction problems thus reducing overheads related to CSP development and maintenance in the future.
Original language | English |
---|---|
Pages (from-to) | 91-100 |
Number of pages | 10 |
Journal | CEUR Workshop Proceedings |
Volume | 3812 |
Publication status | Published - 2024 |
Event | 26th International Workshop on Configuration, ConfWS 2024 - Girona, Spain Duration: 2 Sept 2024 → 3 Sept 2024 |
Keywords
- Automated Generation
- Constraint Satisfaction Problems
- Knowledge Acquisition
- Large Language Models
ASJC Scopus subject areas
- General Computer Science