Scaling Synthetic Logical Reasoning Datasets with Context-Sensitive Declarative Grammars - CRISTAL-MAGNET Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2024

Scaling Synthetic Logical Reasoning Datasets with Context-Sensitive Declarative Grammars

Résumé

Logical reasoning remains a challenge for natural language processing, but it can be improved by training language models to mimic theorem provers on procedurally generated problems. Previous work used domain-specific proof generation algorithms, which biases reasoning toward specific proof traces and limits auditability and extensibility. We present a simpler and more general declarative framework with flexible context-sensitive rules binding multiple languages (specifically, simplified English and the TPTP theorem-proving language). We construct first-order logic problems by selecting up to 32 premises and one hypothesis. We demonstrate that using semantic constraints during generation and careful English verbalization of predicates enhances logical reasoning without hurting natural English tasks. We use relatively small DeBERTa-v3 models to achieve state-of-the-art accuracy on the FOLIO human-authored logic dataset, surpassing GPT-4 in accuracy with or without an external solver by 12%.
Fichier principal
Vignette du fichier
2406.11035v1.pdf (268.76 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04618305 , version 1 (20-06-2024)

Identifiants

Citer

Damien Sileo. Scaling Synthetic Logical Reasoning Datasets with Context-Sensitive Declarative Grammars. 2024. ⟨hal-04618305⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More