Nomological Deductive Reasoning for Trustworthy, Human-Readable, and Actionable AI Outputs

The lack of transparency in many AI systems continues to hinder their adoption in critical domains such as healthcare, finance, and autonomous systems. While recent explainable AI (XAI) methods—particularly those leveraging large language models—have enhanced output readability, they often lack trac...

Full description

Saved in:
Bibliographic Details
Main Authors: Gedeon Hakizimana, Agapito Ledezma Espino
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Algorithms
Subjects:
Online Access:https://www.mdpi.com/1999-4893/18/6/306
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849472652295536640
author Gedeon Hakizimana
Agapito Ledezma Espino
author_facet Gedeon Hakizimana
Agapito Ledezma Espino
author_sort Gedeon Hakizimana
collection DOAJ
description The lack of transparency in many AI systems continues to hinder their adoption in critical domains such as healthcare, finance, and autonomous systems. While recent explainable AI (XAI) methods—particularly those leveraging large language models—have enhanced output readability, they often lack traceable and verifiable reasoning that is aligned with domain-specific logic. This paper presents Nomological Deductive Reasoning (NDR), supported by Nomological Deductive Knowledge Representation (NDKR), as a framework aimed at improving the transparency and auditability of AI decisions through the integration of formal logic and structured domain knowledge. NDR enables the generation of causal, rule-based explanations by validating statistical predictions against symbolic domain constraints. The framework is evaluated on a credit-risk classification task using the Statlog (German Credit Data) dataset, demonstrating that NDR can produce coherent and interpretable explanations consistent with expert-defined logic. While primarily focused on technical integration and deductive validation, the approach lays a foundation for more transparent and norm-compliant AI systems. This work contributes to the growing formalization of XAI by aligning statistical inference with symbolic reasoning, offering a pathway toward more interpretable and verifiable AI decision-making processes.
format Article
id doaj-art-498c9a1eef234ea3991d79495e8bef8b
institution Kabale University
issn 1999-4893
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Algorithms
spelling doaj-art-498c9a1eef234ea3991d79495e8bef8b2025-08-20T03:24:29ZengMDPI AGAlgorithms1999-48932025-05-0118630610.3390/a18060306Nomological Deductive Reasoning for Trustworthy, Human-Readable, and Actionable AI OutputsGedeon Hakizimana0Agapito Ledezma Espino1Department of Computer Science & Engineering, Universidad Carlos III de Madrid, 28911 Leganes, SpainDepartment of Computer Science & Engineering, Universidad Carlos III de Madrid, 28911 Leganes, SpainThe lack of transparency in many AI systems continues to hinder their adoption in critical domains such as healthcare, finance, and autonomous systems. While recent explainable AI (XAI) methods—particularly those leveraging large language models—have enhanced output readability, they often lack traceable and verifiable reasoning that is aligned with domain-specific logic. This paper presents Nomological Deductive Reasoning (NDR), supported by Nomological Deductive Knowledge Representation (NDKR), as a framework aimed at improving the transparency and auditability of AI decisions through the integration of formal logic and structured domain knowledge. NDR enables the generation of causal, rule-based explanations by validating statistical predictions against symbolic domain constraints. The framework is evaluated on a credit-risk classification task using the Statlog (German Credit Data) dataset, demonstrating that NDR can produce coherent and interpretable explanations consistent with expert-defined logic. While primarily focused on technical integration and deductive validation, the approach lays a foundation for more transparent and norm-compliant AI systems. This work contributes to the growing formalization of XAI by aligning statistical inference with symbolic reasoning, offering a pathway toward more interpretable and verifiable AI decision-making processes.https://www.mdpi.com/1999-4893/18/6/306explainable Artificial Intelligence (XAI)interpretable machine learningknowledge representationdeductive reasoningsymbolic reasoningtransparent AI systems
spellingShingle Gedeon Hakizimana
Agapito Ledezma Espino
Nomological Deductive Reasoning for Trustworthy, Human-Readable, and Actionable AI Outputs
Algorithms
explainable Artificial Intelligence (XAI)
interpretable machine learning
knowledge representation
deductive reasoning
symbolic reasoning
transparent AI systems
title Nomological Deductive Reasoning for Trustworthy, Human-Readable, and Actionable AI Outputs
title_full Nomological Deductive Reasoning for Trustworthy, Human-Readable, and Actionable AI Outputs
title_fullStr Nomological Deductive Reasoning for Trustworthy, Human-Readable, and Actionable AI Outputs
title_full_unstemmed Nomological Deductive Reasoning for Trustworthy, Human-Readable, and Actionable AI Outputs
title_short Nomological Deductive Reasoning for Trustworthy, Human-Readable, and Actionable AI Outputs
title_sort nomological deductive reasoning for trustworthy human readable and actionable ai outputs
topic explainable Artificial Intelligence (XAI)
interpretable machine learning
knowledge representation
deductive reasoning
symbolic reasoning
transparent AI systems
url https://www.mdpi.com/1999-4893/18/6/306
work_keys_str_mv AT gedeonhakizimana nomologicaldeductivereasoningfortrustworthyhumanreadableandactionableaioutputs
AT agapitoledezmaespino nomologicaldeductivereasoningfortrustworthyhumanreadableandactionableaioutputs