Explanatory Interactive Machine Learning with Counterexamples from Constrained Large Language Models

In Explanatory Interactive Machine Learning (XIML), counterexamples refine machine learning models by augmenting human feedback. Traditionally created through random sampling or data augmentation, the emergence of Large Language Models (LLMs) now allows an infinite amount of new training instances to be queried through simple natural language prompts. However, validation of LLM results becomes crucial as they may produce potentially inaccurate or “hallucinated” content, which has led to an increased incorporation of logical reasoning with LLMs in recent literature. We present LlmXiml, a framework that integrates logically constrained LLMs into XIML. Our results indicate that LLM-generated counterexamples improve the model performance and logical reasoning increases the counterexamples’ correctness.