NeSy is alive and well: A LLM-driven symbolic approach for better code comment data generation and classification - INRIA - Institut National de Recherche en Informatique et en Automatique Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

NeSy is alive and well: A LLM-driven symbolic approach for better code comment data generation and classification

Résumé

We present a neuro-symbolic (NeSy) workflow combining a symbolic-based learning technique with a large language model (LLM) agent to generate synthetic data for code comment classification in the C programming language. We also show how generating controlled synthetic data using this workflow fixes some of the notable weaknesses of LLM-based generation and increases the performance of classical machine learning models on the code comment classification task. Our best model, a Neural Network, achieves a Macro-F1 score of 91.412% with an increase of 1.033% after data augmentation.
Fichier principal
Vignette du fichier
NeSy is alive and well - Hanna Abi Akl.pdf (668.21 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
licence

Dates et versions

hal-04481420 , version 1 (28-02-2024)

Licence

Identifiants

Citer

Hanna Abi Akl. NeSy is alive and well: A LLM-driven symbolic approach for better code comment data generation and classification. ESWC 2024 - Extended Semantic Web Conference, Albert Meroño Peñuela; Anastasia Dimou; Raphaël Troncy; Olaf Hartig; Maribel Acosta; Mehwish Alam; Heiko Paulheim; Joe Raad; Bruno Sartini, May 2024, Hersonissos, Greece. ⟨hal-04481420⟩
123 Consultations
47 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More