Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

Home › Publications › Neuro-Symbolic Verification of LLM Outputs for Data-Sensitive Domains (extended preprint)

Publication

Neuro-Symbolic Verification of LLM Outputs for Data-Sensitive Domains (extended preprint)

Sigloch, Paul; Benzmüller, Christoph (2026): Neuro-Symbolic Verification of LLM Outputs for Data-Sensitive Domains (extended preprint), in: Bamberg: Otto-Friedrich-Universität.

Details

Faculty/Chair
Faculty/Professorship
Author
Sigloch, Paul
Publisher Information
Otto-Friedrich-Universität : Bamberg
Year of publication
2026
Pages
22
Source/Other editions
Neuro-Symbolic Verification of LLM Outputs for Data-Sensitive Domains (extended preprint), arXiv, 22 Seiten
Year of first publication
2026
Language
English
Licence
URN
Abstract

LLMs deployed in high-stakes domains face fundamental reliability challenges: hallucinations, inconsistencies, and privacy vulnerabilities introduce unacceptable risks where errors carry legal, financial, or safety consequences. This paper presents a hybrid verification architecture combining formal symbolic methods with neural semantic analysis to provide complementary guarantees for LLM-generated content. This architecture employs logical reasoning for input verification, leveraging completeness properties to provide decidable guarantees on structured requirements. For output validation, embedding-based semantic similarity detects contextual hallucinations where formal methods lack expressiveness. This separation is realized in a parallel, actor-based pipeline, addressing limitations of prompt-based self-verification approaches, which inherit the distributional biases that produce hallucinations. The proposed architecture and type-aware verification method are validated with HAIMEDA, a real-world medical device damage assessment reporting system developed through Action Design Research. Evaluation shows hallucination detection rates of over 83% for structured entities and 72% for semantic fabrications, with a 30% reduction in report creation time, demonstrating that neuro-symbolic architectures can provide principled safeguards for LLM deployment in data-sensitive domains.

Keywords
Neuro-symbolic AI
LLM verification
Formal verification
Trustworthy AI
Hybrid AI
Actor model
AI system architecture
Type
Preprint
URI
Activation date
2026-06-15

Permalink: https://fis.uni-bamberg.de/handle/uniba/115590 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-15

Restricted read-only access: login, editing and submission are temporarily disabled.