Shames Al Mandalawi
Affiliation confirmed via AI analysis of OpenAlex, ORCID, and web sources.
DCSTEM Graduate Student Advisor
Also affiliated: University of Arkansas System (2026)
Research Areas
Biography and Research Information
OverviewAI-generated summary
Shames Al Mandalawi's research focuses on the application of large language models (LLMs) and multi-agent architectures for data governance, privacy, and entity resolution. Their work explores policy-aware generative AI for secure data access, investigating coordinated multi-agent systems for automated data governance. Al Mandalawi has also developed novel approaches using LLMs for multilingual customer record linkage and cross-lingual entity resolution. Further research includes privacy-preserving structured knowledge extraction from census-style records and evaluating the semantic and syntactic understanding of LLMs in contexts like payroll systems. The researcher also developed a system for name and address parsing using LLMs. Al Mandalawi has published five papers with a total of seven citations and an h-index of 1. Key collaborators include Mert Can Çakmak, John R. Talburt, and Muzakirruddin Ahmed Mohammed, all from the University of Arkansas at Little Rock.
Metrics
- h-index: 1
- Publications: 7
- Citations: 7
Positions
-
DCSTEM Graduate Student Advisor publications 2025–2026University of Arkansas at Little Rock Institution web page
Selected Publications
-
A Coordinated Multi-agent Architecture for Automated Data Governance Using Large Language Models (2026)
-
Multilingual Customer Record Linkage: A Novel Approach Using LLMs for Cross-Lingual Entity Resolution (2026)
-
Positive Data Control: A Secure Architecture for LLM-Mediated Data Governance (2026)
-
Evaluating Semantic and Syntactic Understanding in Large Language Models for Payroll Systems (2026)
-
A System for Name and Address Parsing with Large Language Models (2026)
-
Policy-Aware Generative AI for Safe, Auditable Data Access Governance (2025)
Collaboration Network
Top Collaborators
- Policy-Aware Generative AI for Safe, Auditable Data Access Governance
- Evaluating Semantic and Syntactic Understanding in Large Language Models for Payroll Systems
- Multilingual Customer Record Linkage: A Novel Approach Using LLMs for Cross-Lingual Entity Resolution
- A Coordinated Multi-agent Architecture for Automated Data Governance Using Large Language Models
- A System for Name and Address Parsing with Large Language Models
- Evaluating Semantic and Syntactic Understanding in Large Language Models for Payroll Systems
- Multilingual Customer Record Linkage: A Novel Approach Using LLMs for Cross-Lingual Entity Resolution
- A System for Name and Address Parsing with Large Language Models
- Evaluating Semantic and Syntactic Understanding in Large Language Models for Payroll Systems
- A Coordinated Multi-agent Architecture for Automated Data Governance Using Large Language Models
- Policy-Aware Generative AI for Safe, Auditable Data Access Governance
- A Coordinated Multi-agent Architecture for Automated Data Governance Using Large Language Models
- Policy-Aware Generative AI for Safe, Auditable Data Access Governance
- Positive Data Control: A Secure Architecture for LLM-Mediated Data Governance
- Policy-Aware Generative AI for Safe, Auditable Data Access Governance
- Positive Data Control: A Secure Architecture for LLM-Mediated Data Governance
- A System for Name and Address Parsing with Large Language Models
- A Coordinated Multi-agent Architecture for Automated Data Governance Using Large Language Models
- A System for Name and Address Parsing with Large Language Models
- Evaluating Semantic and Syntactic Understanding in Large Language Models for Payroll Systems
- Positive Data Control: A Secure Architecture for LLM-Mediated Data Governance
- Multilingual Customer Record Linkage: A Novel Approach Using LLMs for Cross-Lingual Entity Resolution
- A Coordinated Multi-agent Architecture for Automated Data Governance Using Large Language Models
Similar Researchers
Based on overlapping research topics