Open Access

REVIEW

An Analytical Review of Large Language Models Leveraging KDGI Fine-Tuning, Quantum Embedding’s, and Multimodal Architectures

Uddagiri Sirisha^1,*, Chanumolu Kiran Kumar², Revathi Durgam³, Poluru Eswaraiah⁴, G Muni Nagamani⁵

1 Department of Computer Science and Engineering, Prasad V Potluri Siddhartha Institute of Technology, Vijayawada, 520007, India
2 Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, 522302, India
3 Department of Computer Science and Engineering (Data Science), AVN Institute of Engineering and Technology, Hyderabad, 501510, India
4 Department of Computer Science and Engineering (Data Science), Vignan’s Institute of Management and Technology for Women, Hyderabad, 501301, India
5 Department of Computer Science and Engineering, Andhra Loyola Institute of Engineering and Technology, Vijayawada, 520008, India

* Corresponding Author: Uddagiri Sirisha. Email:

(This article belongs to the Special Issue: Enhancing AI Applications through NLP and LLM Integration)

Computers, Materials & Continua 2025, 83(3), 4031-4059. https://doi.org/10.32604/cmc.2025.063721

Received 22 January 2025; Accepted 11 April 2025; Issue published 19 May 2025

Abstract

A complete examination of Large Language Models’ strengths, problems, and applications is needed due to their rising use across disciplines. Current studies frequently focus on single-use situations and lack a comprehensive understanding of LLM architectural performance, strengths, and weaknesses. This gap precludes finding the appropriate models for task-specific applications and limits awareness of emerging LLM optimization and deployment strategies. In this research, 50 studies on 25+ LLMs, including GPT-3, GPT-4, Claude 3.5, DeepKet, and hybrid multimodal frameworks like ContextDET and GeoRSCLIP, are thoroughly reviewed. We propose LLM application taxonomy by grouping techniques by task focus—healthcare, chemistry, sentiment analysis, agent-based simulations, and multimodal integration. Advanced methods like parameter-efficient tuning (LoRA), quantum-enhanced embeddings (DeepKet), retrieval-augmented generation (RAG), and safety-focused models (GalaxyGPT) are evaluated for dataset requirements, computational efficiency, and performance measures. Frameworks for ethical issues, data limited hallucinations, and KDGI-enhanced fine-tuning like Woodpecker’s post-remedy corrections are highlighted. The investigation’s scope, mad, and methods are described, but the primary results are not. The work reveals that domain-specialized fine-tuned LLMs employing RAG and quantum-enhanced embeddings perform better for context-heavy applications. In medical text normalization, ChatGPT-4 outperforms previous models, while two multimodal frameworks, GeoRSCLIP, increase remote sensing. Parameter-efficient tuning technologies like LoRA have minimal computing cost and similar performance, demonstrating the necessity for adaptive models in multiple domains. To discover the optimum domain-specific models, explain domain-specific fine-tuning, and present quantum and multimodal LLMs to address scalability and cross-domain issues. The framework helps academics and practitioners identify, adapt, and innovate LLMs for different purposes. This work advances the field of efficient, interpretable, and ethical LLM application research.

---

Keywords

---