Bridging LLMs and Symbolic Reasoning in Educational QA Systems: Insights from the XAI Challenge at IJCNN 2025

2025-08-02

AI Summary

To address the limited interpretability of large language models (LLMs) in educational question-answering systems, this work proposes a lightweight neuro-symbolic architecture that integrates a fine-tuned, parameter-efficient LLM with a logic-template-based symbolic reasoning module. The Z3 theorem prover is employed to formally encode and automatically verify institutional policy rules, ensuring logical consistency and factual reliability of generated answers. Crucially, symbolic reasoning is embedded directly into the LLM’s response generation pipeline, enabling natural-language explanations tailored to university policy queries. As part of this effort, we organized an international hackathon and released the first high-quality, explanation-annotated dataset for education-policy QA. Experiments demonstrate significant improvements in answer transparency and user trust. This work establishes a reproducible technical pathway and practical paradigm for explainable AI (XAI) in educational AI applications.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Machine Learning: Large Multimodal Models (LMMs)
• Philosophy and Ethics of AI: Accountability, Interpretability & Explainability

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling

Abstract

The growing integration of Artificial Intelligence (AI) into education has intensified the need for transparency and interpretability. While hackathons have long served as agile environments for rapid AI prototyping, few have directly addressed eXplainable AI (XAI) in real-world educational contexts. This paper presents a comprehensive analysis of the XAI Challenge 2025, a hackathon-style competition jointly organized by Ho Chi Minh City University of Technology (HCMUT) and the International Workshop on Trustworthiness and Reliability in Neurosymbolic AI (TRNS-AI), held as part of the International Joint Conference on Neural Networks (IJCNN 2025). The challenge tasked participants with building Question-Answering (QA) systems capable of answering student queries about university policies while generating clear, logic-based natural language explanations. To promote transparency and trustworthiness, solutions were required to use lightweight Large Language Models (LLMs) or hybrid LLM-symbolic systems. A high-quality dataset was provided, constructed via logic-based templates with Z3 validation and refined through expert student review to ensure alignment with real-world academic scenarios. We describe the challenge's motivation, structure, dataset construction, and evaluation protocol. Situating the competition within the broader evolution of AI hackathons, we argue that it represents a novel effort to bridge LLMs and symbolic reasoning in service of explainability. Our findings offer actionable insights for future XAI-centered educational systems and competitive research initiatives.

Problem

• Bridging LLMs and symbolic reasoning for educational QA systems
• Enhancing transparency in AI for real-world educational contexts
• Developing explainable AI solutions for university policy queries

Innovation

• Hybrid LLM-symbolic systems for explainability
• Logic-based templates with Z3 validation
• Lightweight LLMs in educational QA