KEA Explain: Explanations of Hallucinations using Graph Kernel Analysis
This research addresses the reliability of LLMs in high-stakes domains, though it appears incremental as it builds on existing methods for hallucination detection.
The paper tackles the problem of hallucinations in Large Language Models by introducing KEA Explain, a neurosymbolic framework that detects and explains these hallucinations using graph kernel analysis, achieving competitive accuracy in detection tasks.
Large Language Models (LLMs) frequently generate hallucinations: statements that are syntactically plausible but lack factual grounding. This research presents KEA (Kernel-Enriched AI) Explain: a neurosymbolic framework that detects and explains such hallucinations by comparing knowledge graphs constructed from LLM outputs with ground truth data from Wikidata or contextual documents. Using graph kernels and semantic clustering, the method provides explanations for detected hallucinations, ensuring both robustness and interpretability. Our framework achieves competitive accuracy in detecting hallucinations across both open- and closed-domain tasks, and is able to generate contrastive explanations, enhancing transparency. This research advances the reliability of LLMs in high-stakes domains and provides a foundation for future work on precision improvements and multi-source knowledge integration.