EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

KEA Explain: A Neurosymbolic Framework for Explaining LLM Hallucinations

Reilly Haskins, Benjamin Adams

Neurosymbolic Artificial Intelligence · 2026-04 · 2

DOI: 10.1177/29498732261443099 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Neurosymbolic Artificial Intelligence, online erschienen am 25.04.2026. Verfasst von Reilly Haskins und 1 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Zitieren

APA

Haskins, R., & Adams, B. (2026). KEA Explain: A Neurosymbolic Framework for Explaining LLM Hallucinations. Neurosymbolic Artificial Intelligence, 2. https://doi.org/10.1177/29498732261443099

Vancouver

Haskins R, Adams B. KEA Explain: A Neurosymbolic Framework for Explaining LLM Hallucinations. Neurosymbolic Artificial Intelligence. 2026;2. doi:10.1177/29498732261443099

BibTeX
@article{Haskins2026,
  author = {Haskins, Reilly and Adams, Benjamin},
  title = {KEA Explain: A Neurosymbolic Framework for Explaining LLM Hallucinations},
  journal = {Neurosymbolic Artificial Intelligence},
  year = {2026},
  volume = {2},
  doi = {10.1177/29498732261443099}
}
Kostenlos starten →