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

TL;DR

This paper presents Text-JEPA, a lightweight framework that converts natural language into formal logic for explainable question-answering, inspired by dual-process cognition, achieving competitive results with lower computational costs.

Contribution

Introduction of Text-JEPA, a dual-system inspired approach for efficient natural language to logic translation and reasoning in QA systems, with a new evaluation framework.

Findings

Achieves competitive performance with less computational overhead.

Effectively combines neural and symbolic reasoning systems.

Provides a comprehensive evaluation framework for logic translation quality.

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. To address these limitations, we introduce Text-JEPA (Text-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, Text-JEPA emulates System 1 by efficiently generating logic representations, while the Z3 solver operates as System 2, enabling robust logical inference. To 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 Text-JEPA achieves competitive performance with significantly lower computational overhead compared to larger LLM-based systems. Our findings highlight the potential of structured, interpretable reasoning frameworks for building efficient and explainable QA systems in specialized domains.