TRACE-CS: A Hybrid Logic-LLM System for Explainable Course Scheduling

TL;DR

TRACE-CS is a hybrid system that integrates symbolic reasoning and large language models to provide explainable and user-friendly course scheduling solutions, ensuring logical correctness and natural language accessibility.

Contribution

It introduces a novel hybrid approach combining logic-based encoding with LLMs for explainable course scheduling.

Findings

Successfully generates provably correct explanations.

Balances logical correctness with natural language processing.

Addresses fundamental challenges in explainable scheduling systems.

Abstract

We present TRACE-CS, a novel hybrid system that combines symbolic reasoning with large language models (LLMs)to address contrastive queries in course scheduling problems. TRACE-CS leverages logic-based techniques to encode scheduling constraints and generate provably correct explanations, while utilizing an LLM to process natural language queries and refine logical explanations into user friendly responses. This system showcases how combining symbolic KR methods with LLMs creates explainable AI agents that balance logical correctness with natural language accessibility, addressing a fundamental challenge in deployed scheduling systems.