Skip to Content

77 Results Found

  • Article
  • Open Access
1 Citations
4,919 Views
16 Pages

29 July 2025

This study develops a domain-adaptive multimodal RAG (Retrieval-Augmented Generation) system to improve the accuracy and efficiency of technical question answering based on large-scale structured manuals. Using Hyundai Staria maintenance documents as...

(This article belongs to the Special Issue Innovations in Artificial Neural Network Applications)
  • Article
  • Open Access
822 Views
42 Pages

Against the backdrop of digital transformation in higher education, campus information is often dispersed across independent platforms, creating fragmented access and retrieval barriers. To address these challenges, this study proposes a multimodal a...

  • Article
  • Open Access
910 Views
17 Pages

Scaling Regulatory Compliance: A Multi-Agent System with Multimodal RAG for Automated Electrical Installation Inspection Under NOM and NEC Standards

  • Francisco Manuel García-Reyes,
  • Gustavo Castellanos-Guzman,
  • Luis García-Reyes,
  • Fausto Balderas-Jaramillo and ,
  • Roberto Flores-Guerrero and
  • Liliana Gonzalez-Gámez
  • + 1 author+ 0 author

24 May 2026

In electrical systems, it is important to comply with regulations that guarantee the safety and proper functioning of the installation; to validate that this is complied with, it is necessary to have certifications that are carried out by inspectors...

(This article belongs to the Special Issue AI Applications in Modern Industrial Systems)
  • Article
  • Open Access
13 Citations
5,512 Views
22 Pages

Recent advancements in generative AI have fostered the development of highly adept Large Language Models (LLMs) that integrate diverse data types to empower decision-making. Among these, multimodal retrieval-augmented generation (RAG) applications ar...

  • Article
  • Open Access
3 Citations
5,371 Views
18 Pages

HierFinRAG—Hierarchical Multimodal RAG for Financial Document Understanding

  • Quang-Vinh Dang,
  • Ngoc-Son-An Nguyen and
  • Thi-Bich-Diem Vo

Financial document understanding remains a critical challenge for Large Language Models, primarily due to the complex interplay between narrative text and structured numerical tables. Existing Retrieval-Augmented Generation (RAG) systems often treat...

  • Article
  • Open Access
400 Views
40 Pages

30 September 2026

Retrieval-Augmented Generation (RAG) gives language models access to external text and image collections, but it does not make the decisions taken on that content reproducible. Classical Belief–Desire–Intention (BDI) agents provide explic...

(This article belongs to the Special Issue Advanced Applications of Large Language Models)
  • Article
  • Open Access
1,427 Views
21 Pages

18 June 2026

Industrial robot after-sales question answering often depends on multimodal evidence, such as error screenshots, interface displays, and wiring diagrams, which are difficult for conventional text-based retrieval-augmented generation (RAG) systems to...

  • Article
  • Open Access
17 Citations
11,227 Views
20 Pages

29 October 2025

For clinical decision support to work, medical knowledge needs to be easy to find quickly and accurately. Retrieval-Augmented Generation (RAG) systems use big language models and document retrieval to help with diagnostic reasoning, but they could ca...

(This article belongs to the Special Issue Natural Language Processing Based on Neural Networks and Large Language Models)
  • Article
  • Open Access
377 Views
41 Pages

9 October 2026

Blast design in drill-and-blast tunnelling requires geological interpretation and parameter selection for each excavation cycle, yet these tasks are often conducted separately, making it difficult to adapt plans to changing ground conditions. This st...

(This article belongs to the Special Issue Advances in Tunnel Excavation and Underground Construction)
  • Article
  • Open Access
16 Citations
14,769 Views
26 Pages

A Multimodal Framework Embedding Retrieval-Augmented Generation with MLLMs for Eurobarometer Data

  • George Papageorgiou,
  • Vangelis Sarlis,
  • Manolis Maragoudakis and
  • Christos Tjortjis

3 March 2025

This study introduces a multimodal framework integrating retrieval-augmented generation (RAG) with multimodal large language models (MLLMs) to enhance the accessibility, interpretability, and analysis of Eurobarometer survey data. Traditional approac...

  • Article
  • Open Access
10 Citations
2,796 Views
31 Pages

Context-Aware Multi-Agent Architecture for Wildfire Insights

  • Ashen Sandeep,
  • Sithum Jayarathna,
  • Sunera Sandaruwan,
  • Venura Samarappuli and ,
  • Dulani Meedeniya and
  • Charith Perera
  • + 1 author+ 0 author

6 February 2026

Wildfires are environmental hazards with severe ecological, social, and economic impacts. Wildfires devastate ecosystems, communities, and economies worldwide, with rising frequency and intensity driven by climate change, human activity, and environm...

(This article belongs to the Section Internet of Things)
  • Article
  • Open Access
3 Citations
2,489 Views
26 Pages

29 December 2025

Background: Rare diseases often lead to delayed diagnosis because clinical knowledge is fragmented across unstructured research, individual case reports, and heterogeneous data formats. This study presents ZebraMap, a multimodal knowledge map created...

(This article belongs to the Special Issue Explainable Machine Learning in Clinical Diagnostics)
  • Article
  • Open Access
267 Views
26 Pages

ClinLab-RAG: A Multimodal RAG System for the Early Verification of Risks in Medical Equipment Supply Chains

  • Diego Gonzalo Pozo Salas,
  • Pablo Marcel Recalde Varela and
  • Paúl Francisco Baldeón-Egas

Checking manually whether a reagent works on a given analyser takes a median of 12.3 min at the distributor we studied. We developed ClinLab-RAG, a retrieval-augmented generation architecture with hybrid search, a product compatibility graph and five...

(This article belongs to the Special Issue Artificial Intelligence, Machine Learning, and Deep Learning: Innovations and Real-World Applications)
  • Article
  • Open Access
952 Views
23 Pages

TempFinRAG: Multimodal Temporal Retrieval-Augmented Generation for Point-in-Time Financial Question Answering

  • Lanju Tao,
  • Zhengji Li,
  • Yingrui Ji,
  • Chih-Ting Liao and ,
  • Xi Xiao and
  • Xin Cao
  • + 1 author+ 0 author

7 September 2026

Financial question answering is often treated as document question answering, although financial evidence is both multimodal and time-dependent. Semantically equivalent facts expressed in narrative text, tables, page images, or Extensible Business Re...

(This article belongs to the Section A: Computer Science)
  • Article
  • Open Access
2 Citations
1,339 Views
34 Pages

Efficient Similarity-Based Datasheet Retrieval and Analysis Using Retrieval-Augmented Generation for Electronic Component Selection

  • Dan Curavale,
  • Georgian Nicolae,
  • Alexandru Caranica,
  • Horia Cucu and ,
  • Corneliu Burileanu,
  • Valentina Davidoiu,
  • Andi Buzo and
  • Georg Pelz
  • + 3 authors+ 0 author

Component obsolescence and supply-chain disruptions increasingly force engineers to spend significant time manually searching and comparing PDF datasheets to identify compatible replacement parts. We propose an AI-powered datasheet assistant based on...

(This article belongs to the Special Issue AI-Powered Natural Language Processing Applications)
  • Review
  • Open Access
1 Citations
1,516 Views
32 Pages

17 August 2026

Today, data are no longer confined to numerical values arranged in row-by-column matrices or stored neatly within relational databases. One of the defining characteristics of big data is its high variety, encompassing unstructured and multimodal form...

(This article belongs to the Special Issue Applications of Artificial Intelligence and Data Management in Data Analysis)
  • Review
  • Open Access
1 Citations
2,139 Views
32 Pages

Architecting the Orthopedical Clinical AI Pipeline: A Review of Integrating Foundation Models and FHIR for Agentic Clinical Assistants and Digital Twins

  • Assiya Boltaboyeva,
  • Zhanel Baigarayeva,
  • Baglan Imanbek,
  • Bibars Amangeldy and ,
  • Nurdaulet Tasmurzayev,
  • Kassymbek Ozhikenov,
  • Zhadyra Alimbayeva,
  • Chingiz Alimbayev and
  • Nurgul Karymsakova
  • + 4 authors+ 0 author

27 January 2026

The exponential growth of multimodal orthopedic data, ranging from longitudinal Electronic Health Records to high-resolution musculoskeletal imaging, has rendered manual analysis insufficient. This has established Large Language Models (LLMs) as algo...

(This article belongs to the Special Issue Artificial Intelligence Algorithms for Healthcare: 2nd Edition)
  • Article
  • Open Access
2 Citations
1,265 Views
21 Pages

Construction of an Intelligent Risk Identification System for Highway Flood Damage Based on Multimodal Large Models

  • Jinzi Zheng,
  • Zhiyang Liu,
  • Chenguang Li,
  • Hanchu Zhou and ,
  • Erlong Lou,
  • Yaqi Li and
  • Bingou Xu
  • + 2 authors+ 0 author

3 December 2025

Under the increasing threat of extreme weather events, road infrastructure faces significant risks of flood-induced damage. Traditional manual inspection methods are insufficient for modern highway emergency response, which requires higher efficiency...

(This article belongs to the Special Issue Autonomous Vehicles and Robotics—2nd Edition)
  • Article
  • Open Access
292 Views
20 Pages

EduBot: Integrating Federated Learning and RAG for Educational Document Analysis

  • Begüm Erva Şahin,
  • Murat Görkem Çoban,
  • Ahmet Sayar and
  • Meltem Kurt Pehlivanoğlu

15 October 2026

There is a growing demand for intelligent and secure document management systems in the education sector, driven by the exponential growth of digital content. Nevertheless, classic centralized machine learning methods pose major privacy challenges. I...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
6 Citations
3,672 Views
25 Pages

Retrieval-Augmented Generation (RAG) has become a central approach to enhance the factual consistency and domain specificity of large language models (LLMs) by incorporating external context at inference time. However, most existing RAG systems rely...

(This article belongs to the Special Issue AI Synergy: Vision, Language, and Modality)
  • Article
  • Open Access
18 Citations
12,698 Views
30 Pages

4 April 2025

This study investigates prompt engineering (PE) strategies to mitigate hallucination, a key limitation of multimodal large language models (MLLMs). To address this issue, we explore five prominent multimodal PE techniques: in-context learning (ICL),...

  • Article
  • Open Access
248 Views
26 Pages

HEAL-RAG: A Hybrid Evolving Retrieval-Augmented Generation Framework for Explainable Biomedical Data Analysis and Clinical Decision Support

  • Ronke Seyi Babatunde,
  • Sulaiman Olaniyi Abdulsalam,
  • Akeem Femi Kadri,
  • Sherriff Mohammed Kadiri and ,
  • Muhammad Azam,
  • Marvis Ayoola Arowolo,
  • Bola Deborah Ojo,
  • Kayode Abraham Ayantoyinbo and
  • Micheal Olaolu Arowolo
  • + 4 authors+ 0 author

12 November 2026

The rapid growth of biomedical literature, electronic health records (EHRs), and heterogeneous clinical data has created a need for systems that can synthesise evidence to support clinical decision-making. Large language models (LLMs) reason fluently...

(This article belongs to the Special Issue Advanced Algorithms for Biomedical Data Analysis (2nd Edition))
  • Article
  • Open Access
8 Citations
4,095 Views
22 Pages

26 October 2025

This paper presents a protocol-driven hybrid architecture that integrates Retrieval-Augmented Generation (RAG) with two complementary protocols—A Model Context Protocol (MCP) and an Agent Communication Protocol (ACP)—to deliver adaptive,...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
5 Citations
5,628 Views
14 Pages

18 August 2025

With the accelerated digital transformation in education, the efficient integration of massive multimodal instructional resources and the support for interactive question answering (QA) remains a prominent challenge. This study introduces Multimodal...

  • Article
  • Open Access
72 Citations
23,480 Views
17 Pages

9 October 2024

This study examines Retrieval-Augmented Generation (RAG) in large language models (LLMs) and their significant application for undertaking systematic literature reviews (SLRs). RAG-based LLMs can potentially automate tasks like data extraction, summa...

(This article belongs to the Special Issue Data and Text Mining: New Approaches, Achievements and Applications)
  • Review
  • Open Access
7 Citations
3,602 Views
17 Pages

Integrating Fine-Tuning and Retrieval-Augmented Generation for Healthcare AI Systems: A Scoping Review

  • Bernardo G. Collaco,
  • Prabha Srinivasagam,
  • Cesar A. Gomez-Cabello,
  • Syed Ali Haider and ,
  • Ariana Genovese,
  • Nadia G. Wood,
  • Sanjay Bagaria,
  • Mark A. Lifson and
  • Antonio Jorge Forte
  • + 4 authors+ 0 author

(1) Background: Large language models (LLMs) show promise in healthcare but are constrained by hallucinations, static knowledge, and limited domain specificity. Fine-tuning (FT) and retrieval-augmented generation (RAG) offer complementary solutions,...

(This article belongs to the Special Issue Artificial Intelligence in Plastic and Reconstructive Surgery: Innovations and Clinical Applications)
  • Article
  • Open Access
698 Views
19 Pages

RAG-Enhanced Vision–Language Framework and Dataset for Railway Signal Cognition and Safety Reasoning

  • Qunbo Wang,
  • Shiyi Xiong,
  • Jiawei Li,
  • Weiliang Li and ,
  • Chu Huang,
  • Sen Zhang,
  • Xize Guo,
  • Chao Fan and
  • Wenjun Wu
  • + 4 authors+ 0 author

Railway scene understanding is critical for ensuring train operational safety and advancing intelligent railway systems. Existing railway vision methods mainly focus on perception and classification, while lacking regulation-guided semantic reasoning...

  • Article
  • Open Access
2,006 Views
12 Pages

Retrieval-Augmented Vision–Language Agents for Child-Centered Encyclopedia Learning

  • Jing Du,
  • Wenhao Liu,
  • Jingyi Ye,
  • Dibin Zhou and
  • Fuchang Liu

9 October 2025

This study introduces an Encyclopedic Agent for children’s learning that integrates multimodal retrieval with retrieval-augmented generation (RAG). To support this framework, we construct a dataset of 9524 Wikipedia pages covering 935 encyclope...

(This article belongs to the Special Issue Applications of Digital Technology and AI in Educational Settings)
  • Article
  • Open Access
2 Citations
3,111 Views
16 Pages

6 May 2026

Technical documents differ from general text corpora in ways that complicate retrieval-augmented generation (RAG). Evidence for a single answer is often distributed across numbered clauses, tables, figures, captions, and ordered procedures rather tha...

  • Article
  • Open Access
1,869 Views
19 Pages

18 February 2026

This study evaluates whether a multimodal retrieval-augmented generation (RAG) pipeline originally developed for early modern woodcuts can be effectively transferred to the domain of medieval manuscript illumination. Using a dataset of Wenzelsbibel m...

(This article belongs to the Section Digital and Computational History)
  • Proceeding Paper
  • Open Access
1,495 Views
7 Pages

23 December 2025

We integrated retrieval-augmented generation (RAG) with a multimodal large language model (LLM) to cluster large-scale circulation patterns associated with extreme rainfall events (>80 mm day−1) in Taiwan. Employing an event-perspective appr...

(This article belongs to the Proceedings of 8th International Conference on Knowledge Innovation and Invention)
  • Systematic Review
  • Open Access
60 Citations
21,333 Views
90 Pages

Background: Retrieval-augmented generation (RAG) aims to reduce hallucinations and outdated knowledge by grounding LLM outputs in retrieved evidence, but empirical results are scattered across tasks, systems, and metrics, limiting cumulative insight....

(This article belongs to the Special Issue Artificial Intelligence (AI) and Natural Language Processing (NLP))
  • Article
  • Open Access
14 Citations
11,975 Views
22 Pages

15 August 2025

Retrieval-Augmented Generation (RAG) combined with Large Language Models (LLMs) introduces a new paradigm for clinical-trial data analysis that is both real-time and knowledge-traceable. This study targets a multi-site, real-world data environment. I...

  • Article
  • Open Access
6 Citations
1,354 Views
34 Pages

Traditional automated monitoring systems adopted for Intersection Traffic Control still face challenges, including high costs, maintenance difficulties, insufficient coverage, poor multimodal data integration, and limited traffic information analysis...

(This article belongs to the Special Issue Interactive Design for Autonomous Driving Vehicles)
  • Article
  • Open Access
1 Citations
869 Views
30 Pages

Multi-source heterogeneous data in discrete manufacturing shop floors, including vibration signals, equipment logs, visual monitoring data, and handwritten production reports, exhibit significant differences in modality and semantic representation. T...

(This article belongs to the Section Computer Science & Engineering)
  • Article
  • Open Access
637 Views
28 Pages

17 August 2026

Retrieval-augmented generation (RAG) with large language models (LLMs) provides a new technical pathway for integrating industrial-domain knowledge with the reasoning capabilities of LLMs and has substantial application potential in sustainable indus...

(This article belongs to the Special Issue Advances in Industrial Engineering and Management Towards Sustainable Development Goals)
  • Article
  • Open Access
5 Citations
2,711 Views
25 Pages

Improved Flood Management and Risk Communication Through Large Language Models

  • Divas Karimanzira,
  • Thomas Rauschenbach,
  • Tobias Hellmund and
  • Linda Ritzau

12 November 2025

In light of urbanization, climate change, and the escalation of extreme weather events, flood management is becoming more and more important. Improving community resilience and reducing flood risks require prompt decision-making and effective communi...

(This article belongs to the Special Issue Artificial Intelligence Algorithms in Sustainability)
  • Proceeding Paper
  • Open Access
1,668 Views
10 Pages

22 December 2025

Extreme autumn rainfall has become frequent due to climate change, making disaster prevention increasingly difficult. We combined a retrieval-augmented generation (RAG) framework with a multimodal large language model (multimodal LLM) to automaticall...

(This article belongs to the Proceedings of 8th International Conference on Knowledge Innovation and Invention)
  • Article
  • Open Access
11 Citations
5,006 Views
48 Pages

ResQConnect: An AI-Powered Multi-Agentic Platform for Human-Centered and Resilient Disaster Response

  • Savinu Aththanayake,
  • Chemini Mallikarachchi,
  • Janeesha Wickramasinghe,
  • Sajeev Kugarajah and ,
  • Dulani Meedeniya and
  • Biswajeet Pradhan
  • + 1 author+ 0 author

19 January 2026

Effective disaster management is critical for safeguarding lives, infrastructure and economies in an era of escalating natural hazards like floods and landslides. Despite advanced early-warning systems and coordination frameworks, a persistent &ldquo...

(This article belongs to the Section Environmental Sustainability and Applications)
  • Article
  • Open Access
392 Views
57 Pages

Multimodal Knowledge Graphs (MMKGs) offer a promising paradigm for integrating heterogeneous sources into a unified, queryable, semantically structured representation. However, existing MMKG construction pipelines remain predominantly text-centric, e...

  • Article
  • Open Access
1,006 Views
15 Pages

Accurate Multi-Page Document Retrieval by Effectively Fusing Context Information Across Pages

  • Bing Qian,
  • Kaiwei Deng,
  • Yuexin Wu,
  • Jianming Zhang and ,
  • Juanjuan Sun,
  • Yanru Xue and
  • Chunxiao Fan
  • + 2 authors+ 0 author

Visual retrievers such as visual retrieval-augmented generation (RAG) have recently emerged as a powerful model for retrieving multimodal documents without the need to convert page images into text. Existing visual retrievers typically encode every d...

(This article belongs to the Special Issue Advances in AI for Data Analytics and Intelligent Systems)
  • Feature Paper
  • Article
  • Open Access
6 Citations
5,389 Views
34 Pages

26 May 2025

This preliminary study covers the construction and application of a Graph-based Retrieval-Augmented Generation (GraphRAG) system integrating a multimodal LLM, Large Language and Vision Assistant (LLaVA) with graph database software (Neo4j) to enhance...

(This article belongs to the Special Issue Feature Papers in Smart Sensing and Intelligent Sensors 2025)
  • Article
  • Open Access
435 Views
26 Pages

The integration of multimodal athletic data, including wearable monitoring, self-reports, and training schedules presents a growing opportunity for machine learning to support individualized recovery decision-making. We present a feasibility study th...

(This article belongs to the Section Artificial Intelligence-Based Technologies)
  • Project Report
  • Open Access
1 Citations
908 Views
20 Pages

Artificial Intelligence for Musical Cultural Heritage: Preservation, Interpretation, and Human-Centered Creativity at the Centro di Sonologia Computazionale

  • Sara Giuriati,
  • Anna Zuccante,
  • Alessandro Russo,
  • Alessandro Fiordelmondo and ,
  • Matteo Spanio,
  • Antonio Rodà and
  • Sergio Canazza
  • + 2 authors+ 0 author

28 August 2026

Artificial intelligence is increasingly shaping the preservation, interpretation, management, and reactivation of musical cultural heritage, especially in domains affected by technological obsolescence such as computer music, electroacoustic works, a...

  • Article
  • Open Access
1,183 Views
30 Pages

Agentic AI-Driven Cultivation Advisory and Symptom-Level Diagnostic Support in a Controlled Indoor Farming System

  • Jutarut Chaoraingern,
  • Akarat Pattaraanuvong,
  • Kantapon Paraksa,
  • Kantiporn Khunthong and ,
  • Tirawat Nontiwantok and
  • Arjin Numsomran
  • + 1 author+ 0 author

Small-scale and urban indoor farms typically rely on manual observation, which delays stress detection and yields inconsistent crop quality. While large language models (LLMs) and retrieval-augmented generation (RAG) have been explored for agricultur...

  • Article
  • Open Access
7 Citations
3,122 Views
17 Pages

14 November 2025

This study evaluates the performance of seven large language models (LLMs) in generating context-aware recommendations. The system is built on a collection of PDF documents (brochures) describing local events and activities, which are embedded into a...

(This article belongs to the Special Issue Recent Advances and Applications of Machine Learning in Pattern Recognition)
  • Article
  • Open Access
6 Citations
5,161 Views
27 Pages

18 November 2025

Large Language Models (LLMs) and Multimodal Models (LMMs) are significantly influencing scientific research, including archaeology—a discipline dealing with uniquely complex, multimodal data. This comprehensive review systematically examines re...

(This article belongs to the Special Issue Electronics and Computer Science for Cultural Heritage: Advancements, Preservation, and Applications, 2nd Edition)
  • Review
  • Open Access
8,132 Views
18 Pages

Artificial intelligence architecture is no longer adequately described by model size alone. Dense Transformers remain the reference architecture for language and multimodal reasoning, but production systems increasingly combine conditional computatio...

(This article belongs to the Special Issue AI-Driven IoT: Beyond Connectivity, Toward Intelligence)
  • Article
  • Open Access
5 Citations
7,294 Views
50 Pages

A Comprehensive Review of AI Advancement Using testFAILS and testFAILS-2 for the Pursuit of AGI

  • Yulia Kumar,
  • Mengtian Lin,
  • Christopher Paredes,
  • Dan Li and ,
  • Guohao Yang,
  • Dov Kruger,
  • J. Jenny Li and
  • Patricia Morreale
  • + 3 authors+ 0 author

18 December 2024

In a previous paper we defined testFAILS, a set of benchmarks for measuring the efficacy of Large Language Models in various domains. This paper defines a second-generation framework, testFAILS-2 to measure how current AI engines are progressing towa...

(This article belongs to the Section Artificial Intelligence)
  • Feature Paper
  • Article
  • Open Access
1 Citations
1,776 Views
23 Pages

Evidence-Guided Diagnostic Reasoning for Pediatric Chest Radiology Based on Multimodal Large Language Models

  • Yuze Zhao,
  • Qing Wang,
  • Yingwen Wang,
  • Ruiwei Zhao and ,
  • Rui Feng and
  • Xiaobo Zhang
  • + 1 author+ 0 author

Pediatric respiratory diseases are a leading cause of hospital admissions and childhood mortality worldwide, highlighting the critical need for accurate and timely diagnosis to support effective treatment and long-term care. Chest radiography remains...

(This article belongs to the Section AI in Imaging)

of 2