CSLV: Cross-Source Logical Validation for Reducing Source-Induced Reasoning Bias in Large Language Models

Fuente: Zenodo
Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Khan, Alim ul haq
Format: Recurso digital
Sprache:Englisch
Veröffentlicht: Zenodo 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866902124858703872
author Khan, Alim ul haq
author_facet Khan, Alim ul haq
contents <p>This work introduces CSLV (Cross-Source Logical Validation), a framework designed to detect and mitigate source-induced reasoning bias in large language models. The approach evaluates the logical consistency between the original query, provided examples, and the model's generated reasoning.</p> <p>The report also evaluates ANIMA, a cognitive architecture concept that integrates identity-based memory structures and validation layers to enhance reasoning reliability in AI systems.</p> <p>Experimental validation and conceptual analysis are provided to demonstrate how cross-source validation can reduce hallucination and example-dependency in LLM outputs.</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_18965451
institution Zenodo
language eng
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle CSLV: Cross-Source Logical Validation for Reducing Source-Induced Reasoning Bias in Large Language Models
Khan, Alim ul haq
Artificial Intelligence Large Language Models Hallucination Reasoning Validation CSLV ANIMA AI Safety Cognitive Architecture
<p>This work introduces CSLV (Cross-Source Logical Validation), a framework designed to detect and mitigate source-induced reasoning bias in large language models. The approach evaluates the logical consistency between the original query, provided examples, and the model's generated reasoning.</p> <p>The report also evaluates ANIMA, a cognitive architecture concept that integrates identity-based memory structures and validation layers to enhance reasoning reliability in AI systems.</p> <p>Experimental validation and conceptual analysis are provided to demonstrate how cross-source validation can reduce hallucination and example-dependency in LLM outputs.</p>
title CSLV: Cross-Source Logical Validation for Reducing Source-Induced Reasoning Bias in Large Language Models
topic Artificial Intelligence Large Language Models Hallucination Reasoning Validation CSLV ANIMA AI Safety Cognitive Architecture
url https://doi.org/10.5281/zenodo.18965451