Scaling Synthetic Logical Reasoning Datasets with Context-Sensitive Declarative Grammars

Sileo, Damien

Document type :

Pré-publication ou Document de travail

Permalink :

http://hdl.handle.net/20.500.12210/115311

Title :

Scaling Synthetic Logical Reasoning Datasets with Context-Sensitive Declarative Grammars

Author(s) :

Sileo, Damien [Auteur]
Centrale Lille
Université de Lille
Machine Learning in Information Networks [MAGNET]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]

HAL domain(s) :

Informatique [cs]

English abstract : [en]

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 ...
Show more >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%.Show less >

Language :

Anglais

Collections :