Generating Streamlining Constraints with Large Language Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Voboril, Florentina, Ramaswamy, Vaidyanathan Peruvemba, Szeider, Stefan
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909909706080256
author Voboril, Florentina
Ramaswamy, Vaidyanathan Peruvemba
Szeider, Stefan
author_facet Voboril, Florentina
Ramaswamy, Vaidyanathan Peruvemba
Szeider, Stefan
contents Streamlining constraints (or streamliners, for short) narrow the search space, enhancing the speed and feasibility of solving complex constraint satisfaction problems. Traditionally, streamliners were crafted manually or generated through systematically combined atomic constraints with high-effort offline testing. Our approach utilizes the creativity of Large Language Models (LLMs) to propose effective streamliners for problems specified in the MiniZinc constraint programming language and integrates feedback to the LLM with quick empirical tests for validation. Evaluated across seven diverse constraint satisfaction problems, our method achieves substantial runtime reductions. We compare the results to obfuscated and disguised variants of the problem to see whether the results depend on LLM memorization. We also analyze whether longer off-line runs improve the quality of streamliners and whether the LLM can propose good combinations of streamliners.
format Preprint
id arxiv_https___arxiv_org_abs_2408_10268
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Generating Streamlining Constraints with Large Language Models
Voboril, Florentina
Ramaswamy, Vaidyanathan Peruvemba
Szeider, Stefan
Software Engineering
Artificial Intelligence
Machine Learning
Streamlining constraints (or streamliners, for short) narrow the search space, enhancing the speed and feasibility of solving complex constraint satisfaction problems. Traditionally, streamliners were crafted manually or generated through systematically combined atomic constraints with high-effort offline testing. Our approach utilizes the creativity of Large Language Models (LLMs) to propose effective streamliners for problems specified in the MiniZinc constraint programming language and integrates feedback to the LLM with quick empirical tests for validation. Evaluated across seven diverse constraint satisfaction problems, our method achieves substantial runtime reductions. We compare the results to obfuscated and disguised variants of the problem to see whether the results depend on LLM memorization. We also analyze whether longer off-line runs improve the quality of streamliners and whether the LLM can propose good combinations of streamliners.
title Generating Streamlining Constraints with Large Language Models
topic Software Engineering
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2408.10268