TRACE-CS: A Hybrid Logic-LLM System for Explainable Course Scheduling
This addresses the challenge of explainability in deployed scheduling systems for users needing accessible and correct explanations.
The paper tackles the problem of handling contrastive queries in course scheduling by developing TRACE-CS, a hybrid system that combines symbolic reasoning with large language models, resulting in an explainable AI agent that balances logical correctness with natural language accessibility.
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.