Enregistré dans:
Détails bibliographiques
Auteurs principaux: Régin, Florian, De Maria, Elisabetta, Bonlarron, Alexandre
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2407.13490
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929514404118528
author Régin, Florian
De Maria, Elisabetta
Bonlarron, Alexandre
author_facet Régin, Florian
De Maria, Elisabetta
Bonlarron, Alexandre
contents 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 GenCP, an improved version of On-the-fly Constraint Programming Search (OTFS) using LLM-generated domains. Compared to Beam Search (BS), a standard NLP method, this combined approach (GenCP 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.
format Preprint
id arxiv_https___arxiv_org_abs_2407_13490
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Combining Constraint Programming Reasoning with Large Language Model Predictions
Régin, Florian
De Maria, Elisabetta
Bonlarron, Alexandre
Computation and Language
Artificial Intelligence
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 GenCP, an improved version of On-the-fly Constraint Programming Search (OTFS) using LLM-generated domains. Compared to Beam Search (BS), a standard NLP method, this combined approach (GenCP 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.
title Combining Constraint Programming Reasoning with Large Language Model Predictions
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2407.13490