Enhancing parametric and causal reasoning through a formula-augmented language model approach for belt grinding knowledge assistance

Zhou, Tianyu, Zou, Lai and Wang, Wenxi 2026. Enhancing parametric and causal reasoning through a formula-augmented language model approach for belt grinding knowledge assistance. Engineering Applications of Artificial Intelligence 185 , 116505. 10.1016/j.engappai.2026.116505

Full text not available from this repository.

Abstract

Abrasive belt grinding is a flexible surface finishing process in which precision machining of geometrically complex components often involves coupled parameters and contact mechanisms. Retrieval-augmented large language models (LLMs) have shown promise in domain-specific knowledge questioning. However, their capabilities in numerical computation and mechanism-oriented reasoning remain limited in scenarios involving coupled parameters. This study introduces a structural enhancement mechanism based on formula-group embedding. It integrates formula retrieval, task classification, structured prompting, and code execution into the conventional retrieval-augmented generation (RAG) pipeline. The approach addresses numerical computation and mechanistic reasoning in belt grinding and is validated through contact modeling, a representative core problem of the process. In numerical computation tasks, the proposed method achieved 100% accuracy in basic cases. In more challenging scenarios, it reached 90% accuracy with an average deviation within 5%. In contrast, for these complex tasks, general-purpose LLMs achieved only about a 10% pass rate. In mechanism-related reasoning tasks, utilizing a hybrid expert-LLM evaluation, the method demonstrated a 13.1% improvement over the second-best model and a 36.6% gain over the baseline without formula augmentation. These results indicate that the proposed mechanism provides value in improving the reliability of numerical computation and the coherence of mechanistic reasoning.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Schools > Engineering
Publisher:	Elsevier
ISSN:	0952-1976
Date of Acceptance:	7 October 2026
Last Modified:	21 Oct 2026 14:00
URI:	https://orca.cardiff.ac.uk/id/eprint/190355

Actions (repository staff only)

Edit Item