Speaking in Words, Thinking in Logic: A Dual-Process Framework in QA Systems

Ho Chi Minh City University of T echnology (HCMUT), Vietnam National University - Ho Chi Minh City Ho Chi Minh City, Vietnam sang.nguyen.imp21@hcmut.edu.vn Abstract --Recent advances in large language models (LLMs) have significantly enhanced question-answering (QA) capabilities, particularly in open-domain contexts. However, in closed-domain scenarios such as education, healthcare, and law, users demand not only accurate answers but also transparent reasoning and explainable decision-making processes. While neural-symbolic (NeSy) frameworks have emerged as a promising solution--leveraging LLMs for natural language understanding and symbolic systems for formal reasoning--existing approaches often rely on large-scale models and exhibit inefficiencies in translating natural language into formal logic representations. T o address these limitations, we introduce T ext-JEPA (T ext-based Joint-Embedding Predictive Architecture), a lightweight yet effective framework for converting natural language into first-order logic (NL2FOL). Drawing inspiration from dual-system cognitive theory, T ext-JEPA emulates System 1 by efficiently generating logic representations, while the Z3 solver operates as System 2, enabling robust logical inference. T o rigorously evaluate the NL2FOL-to-reasoning pipeline, we propose a comprehensive evaluation framework comprising three custom metrics: conversion score, reasoning score, and Spearman rho score, which collectively capture the quality of logical translation and its downstream impact on reasoning accuracy. Empirical results on domain-specific datasets demonstrate that T ext-JEPA achieves competitive performance with significantly lower computational overhead compared to larger LLM-based systems.