Ramandeep Singh Dehal

Mr. Ramandeep Singh Dehal

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
RDRamandeep Singh Dehal
Ramandeep Singh Dehal
MSMehak Sharma
Mehak Sharma
EREnayat Rajabi
Enayat Rajabi
The reciprocal relationship between Large Language Models (LLMs) and Knowledge Graphs (KGs) highlights their synergistic potential in enhancing artificial intelligence (AI) applications. LLMs, with their natural language understanding and generative capabilities, support the automation of KG construction through entity recognition, relation extraction, and schema generation. Conversely, KGs serve as structured and interpretable data sources that improve the transparency, factual consistency and reliability of LLM-based applications, mitigating challenges such as hallucinations and lack of explainability. This study conducts a systematic literature review of 77 studies to examine AI methodologies supporting LLM–KG integration, including symbolic AI, machine learning, and hybrid approaches. The research explores diverse applications spanning healthcare, finance, justice, and industrial automation, revealing the transformative potential of this synergy. Through in-depth analysis, this study identifies key limitations in current approaches, including challenges in scalability with maintaining dynamic and real-time Knowledge Graphs, difficulty in adapting general-purpose LLMs to specialized domains, limited explainability in tracing model outputs to interpretable reasoning, and ethical concerns surrounding bias, fairness, and transparency. In response, the study highlights potential strategies to optimize LLM–KG synergy. The findings from this study provide actionable insights for researchers and practitioners aiming for robust, transparent, and adaptive AI systems to enhance knowledge-driven AI applications through LLM–KG integration, further advancing generative AI and explainable AI (XAI) applications.

14 April 2024
Verified
Conference Paper
Open access
RDRamandeep Singh Dehal
Ramandeep Singh Dehal
MSMehak Sharma
Mehak Sharma
RSRonnie de Souza Santos
Ronnie de Souza Santos
Algorithmic discrimination is a condition that arises when data-driven software unfairly treats users based on attributes like ethnicity, race, gender, sexual orientation, religion, age, disability, or other personal characteristics. Nowadays, as machine learning gains popularity, cases of algorithmic discrimination are increasingly being reported in several contexts. This study delves into various studies published over the years reporting algorithmic discrimination. We aim to support software engineering researchers and practitioners in addressing this issue by discussing key characteristics of the problem. LAY In recent years, data bias has posed significant challenges for minority groups, leading to systems and algorithms discriminating against Women, Black communities, people with disabilities, and LGBTQIA+ individuals. Recognizing this bias is the crucial first step toward devising solutions. This study maps and discusses instances of algorithmic discrimination across various societal domains.