From Argumentation to Labeled Logic Program for LLM Verification
Proceedings of the AAAI Symposium Series · 18.05.2026 · 8 (1) · 411-419
DOI: 10.1609/aaaiss.v8i1.42572 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Symposium Series, online erschienen am 18.05.2026. Verfasst von Boris Galitsky.
Abstract (Originalsprache)
Large language models (LLMs) often generate fluent but in-correct or unsupported statements, commonly referred to as hallucinations. We propose a hallucination detection frame-work based on a Labeled Logic Program (LLP) architecture that integrates multiple reasoning paradigms, including logic programming, argumentation, probabilistic inference, and ab-ductive explanation. By enriching symbolic rules with seman-tic, epistemic, and contextual labels and applying discourse-aware weighting, the system prioritizes nucleus claims over peripheral statements during verification. Experiments on three benchmark datasets and a challenging clinical narrative dataset show that LLP consistently outperforms classical symbolic validators, achieving the highest detection accuracy when combined with discourse modeling. A human evaluation further demonstrates that logic-assisted explanations im-prove both hallucination detection accuracy and user trust. The results suggest that labeled symbolic reasoning with dis-course awareness provides a robust and interpretable ap-proach to LLM verification in safety-critical domains.
Zitieren
APA
Galitsky, B. (2026). From Argumentation to Labeled Logic Program for LLM Verification. Proceedings of the AAAI Symposium Series, 8(1), 411-419. https://doi.org/10.1609/aaaiss.v8i1.42572
Vancouver
Galitsky B. From Argumentation to Labeled Logic Program for LLM Verification. Proceedings of the AAAI Symposium Series. 2026;8(1):411-419. doi:10.1609/aaaiss.v8i1.42572
BibTeX
@article{Galitsky2026,
author = {Galitsky, Boris},
title = {From Argumentation to Labeled Logic Program for LLM Verification},
journal = {Proceedings of the AAAI Symposium Series},
year = {2026},
volume = {8},
number = {1},
pages = {411--419},
doi = {10.1609/aaaiss.v8i1.42572}
}
EUVIMED