Littérature scientifique sur le sujet « Knowledge Graph-based Retrieval Augmented Generation (KG-RAG) »
Créez une référence correcte selon les styles APA, MLA, Chicago, Harvard et plusieurs autres
Consultez les listes thématiques d’articles de revues, de livres, de thèses, de rapports de conférences et d’autres sources académiques sur le sujet « Knowledge Graph-based Retrieval Augmented Generation (KG-RAG) ».
À côté de chaque source dans la liste de références il y a un bouton « Ajouter à la bibliographie ». Cliquez sur ce bouton, et nous générerons automatiquement la référence bibliographique pour la source choisie selon votre style de citation préféré : APA, MLA, Harvard, Vancouver, Chicago, etc.
Vous pouvez aussi télécharger le texte intégral de la publication scolaire au format pdf et consulter son résumé en ligne lorsque ces informations sont inclues dans les métadonnées.
Articles de revues sur le sujet "Knowledge Graph-based Retrieval Augmented Generation (KG-RAG)"
1
Tian, Shiyu, Shuyue Xing, Xingrui Li, Yangyang Luo, Caixia Yuan, Wei Chen, Huixing Jiang et Xiaojie Wang. « A Systematic Exploration of Knowledge Graph Alignment with Large Language Models in Retrieval Augmented Generation ». Proceedings of the AAAI Conference on Artificial Intelligence 39, no 24 (11 avril 2025) : 25291–99. https://doi.org/10.1609/aaai.v39i24.34716.
Texte intégralRésumé :
Retrieval Augmented Generation (RAG) with Knowledge Graphs (KGs) is an effective way to enhance Large Language Models (LLMs). Due to the natural discrepancy between structured KGs and sequential LLMs, KGs must be linearized to text before being inputted into LLMs, leading to the problem of KG Alignment with LLMs (KGA). However, recent KG+RAG methods only consider KGA as a simple step without comprehensive and in-depth explorations, leaving three essential problems unclear: (1) What are the factors and their effects in KGA? (2) How do LLMs understand KGs? (3) How to improve KG+RAG by KGA? To fill this gap, we conduct systematic explorations on KGA, where we first define the problem of KGA and subdivide it into the graph transformation phase (graph-to-graph) and the linearization phase (graph-to-text). In the graph transformation phase, we study graph features at the node, edge, and full graph levels from low to high granularity. In the linearization phase, we study factors on formats, orders, and templates from structural to token levels. We conduct substantial experiments on 15 typical LLMs and three common datasets. Our main findings include: (1) The centrality of the KG affects the final generation; formats have the greatest impact on KGA; orders are model-dependent, without an optimal order adapting for all models; the templates with special token separators are better. (2) LLMs understand KGs by a unique mechanism, different from processing natural sentences, and separators play an important role. (3) We achieved 7.3% average performance improvements on four common LLMs on the KGQA task by combining the optimal factors to enhance KGA.
2
Hamza, Ameer, Abdullah, Yong Hyun Ahn, Sungyoung Lee et Seong Tae Kim. « LLaVA Needs More Knowledge : Retrieval Augmented Natural Language Generation with Knowledge Graph for Explaining Thoracic Pathologies ». Proceedings of the AAAI Conference on Artificial Intelligence 39, no 3 (11 avril 2025) : 3311–19. https://doi.org/10.1609/aaai.v39i3.32342.
Texte intégralRésumé :
Generating Natural Language Explanations (NLEs) for model predictions on medical images, particularly those depicting thoracic pathologies, remains a critical and challenging task. Existing methodologies often struggle due to general models' insufficient domain-specific medical knowledge and privacy concerns associated with retrieval-based augmentation techniques. To address these issues, we propose a novel Vision-Language framework augmented with a Knowledge Graph (KG)-based datastore, which enhances the model's understanding by incorporating additional domain-specific medical knowledge essential for generating accurate and informative NLEs. Our framework employs a KG-based retrieval mechanism that not only improves the precision of the generated explanations but also preserves data privacy by avoiding direct data retrieval. The KG datastore is designed as a plug-and-play module, allowing for seamless integration with various model architectures. We introduce and evaluate three distinct frameworks within this paradigm: KG-LLaVA, which integrates the pre-trained LLaVA model with KG-RAG; Med-XPT, a custom framework combining MedCLIP, a transformer-based projector, and GPT-2; and Bio-LLaVA, which adapts LLaVA by incorporating the Bio-ViT-L vision model. These frameworks are validated on the MIMIC-NLE dataset, where they achieve state-of-the-art results, underscoring the effectiveness of KG augmentation in generating high-quality NLEs for thoracic pathologies.
3
Song, Sihan, Chuncheng Yang, Li Xu, Haibin Shang, Zhuo Li et Yinghui Chang. « TravelRAG : A Tourist Attraction Retrieval Framework Based on Multi-Layer Knowledge Graph ». ISPRS International Journal of Geo-Information 13, no 11 (16 novembre 2024) : 414. http://dx.doi.org/10.3390/ijgi13110414.
Texte intégralRésumé :
A novel framework called TravelRAG is introduced in this paper, which is built upon a large language model (LLM) and integrates Retrieval-Augmented Generation (RAG) with knowledge graphs to create a retrieval system framework designed for the tourism domain. This framework seeks to address the challenges LLMs face in providing precise and contextually appropriate responses to domain-specific queries in the tourism field. TravelRAG extracts information related to tourist attractions from User-Generated Content (UGC) on social media platforms and organizes it into a multi-layer knowledge graph. The travel knowledge graph serves as the core retrieval source for the LLM, enhancing the accuracy of information retrieval and significantly reducing the generation of erroneous or fabricated responses, often termed as “hallucinations”. As a result, the accuracy of the LLM’s output is enhanced. Comparative analyses with traditional RAG pipelines indicate that TravelRAG significantly boosts both the retrieval efficiency and accuracy, while also greatly reducing the computational cost of model fine-tuning. The experimental results show that TravelRAG not only outperforms traditional methods in terms of retrieval accuracy but also better meets user needs for content generation.
4
Saran Raj. S et Dr. C. Meenakshi. « A Smart Legal Assistant for Indian Laws ». International Journal of Latest Technology in Engineering Management & ; Applied Science 14, no 4 (15 mai 2025) : 588–92. https://doi.org/10.51583/ijltemas.2025.140400064.
Texte intégralRésumé :
Abstract: This project proposes a chatbot system that integrates Retrieval-Augmented Generation (RAG) and a Knowledge Graph (KG) to address queries on Indian law. The system dynamically adapts to the complexity of user queries to optimize performance and accuracy. For straightforward questions, the RAG module retrieves relevant legal documents and generates concise answers. For complex, multi-faceted queries, the system employs a multihop reasoning approach using the knowledge graph to derive accurate and context- aware responses.To enhance accessibility and inclusivity, the chatbot supports multiple regional languages, enabling users from diverse linguistic backgrounds to interact with the system in their preferred language. This hybrid design ensures efficient computation by selectively engaging the KG only when necessary, reducing resource usage while maintaining high accuracy.The chatbot provides users with seamless access to legal insights, offering quick answers for simple queries and in- depth reasoning for complex cases. By combining the strengths of RAG and KG, this system aims to revolutionize legal assistance by improving accessibility, precision, and usability for both legal professionals and the general public, empowering users to navigate Indian law with confidence and efficiency.
5
Zhang, Haiyu, Yinghui Zhao, Boyu Sun, Yaqi Wu, Zetian Fu et Xinqing Xiao. « Large Language Model Based Intelligent Fault Information Retrieval System for New Energy Vehicles ». Applied Sciences 15, no 7 (6 avril 2025) : 4034. https://doi.org/10.3390/app15074034.
Texte intégralRésumé :
In recent years, the rapid development of the new energy vehicle (NEV) industry has exposed significant deficiencies in intelligent fault diagnosis and information retrieval technologies, especially in intelligent fault information retrieval, which faces persistent challenges including inadequate system adaptability and reasoning bottlenecks. To address these challenges, this study proposes a Retrieval-Augmented Generation (RAG) framework that integrates large language models (LLMs) with knowledge graphs (KGs). The framework consists of three key components: fault data collection, knowledge graph construction, and fault knowledge model training. The primary research contributions are threefold: (1) A domain-optimized fine-tuning strategy for LLMs based on NEV fault characteristics, verifying the superior accuracy of the Bidirectional Encoder Representations from Transformers (BERT) model in fault classification tasks. (2) A structured knowledge graph encompassing 122 fault categories, developed through the ChatGLM3-6B model completing named entity and knowledge relation extraction to generate fault knowledge and build a paraphrased vocabulary. (3) An intelligent fault information retrieval system that significantly outperforms traditional models in NEV-specific Q&A scenarios, providing multi-level fault cause analysis and actionable solution recommendations.
6
Martin, Andreas, Hans Friedrich Witschel, Maximilian Mandl et Mona Stockhecke. « Semantic Verification in Large Language Model-based Retrieval Augmented Generation ». Proceedings of the AAAI Symposium Series 3, no 1 (20 mai 2024) : 188–92. http://dx.doi.org/10.1609/aaaiss.v3i1.31199.
Texte intégralRésumé :
This position paper presents a novel approach of semantic verification in Large Language Model-based Retrieval Augmented Generation (LLM-RAG) systems, focusing on the critical need for factually accurate information dissemination during public debates, especially prior to plebiscites e.g. in direct democracies, particularly in the context of Switzerland. Recognizing the unique challenges posed by the current generation of Large Language Models (LLMs) in maintaining factual integrity, this research proposes an innovative solution that integrates retrieval mechanisms with enhanced semantic verification processes. The paper outlines a comprehensive methodology following a Design Science Research approach, which includes defining user personas, designing conversational interfaces, and iteratively developing a hybrid dialogue system. Central to this system is a robust semantic verification framework that leverages a knowledge graph for fact-checking and validation, ensuring the correctness and consistency of information generated by LLMs. The paper discusses the significance of this research in the context of Swiss direct democracy, where informed decision-making is pivotal. By improving the accuracy and reliability of information provided to the public, the proposed system aims to support the democratic process, enabling citizens to make well-informed decisions on complex issues. The research contributes to advancing the field of natural language processing and information retrieval, demonstrating the potential of AI and LLMs in enhancing civic engagement and democratic participation.
7
Yao, Yao, et Horacio González–Vélez. « AI-Powered System to Facilitate Personalized Adaptive Learning in Digital Transformation ». Applied Sciences 15, no 9 (30 avril 2025) : 4989. https://doi.org/10.3390/app15094989.
Texte intégralRésumé :
As Large Language Models (LLMs) incorporate generative Artificial Intelligence (AI) and complex machine learning algorithms, they have proven to be highly effective in assisting human users with complex professional tasks through natural language interaction. However, in addition to their current capabilities, LLMs occasionally generate responses that contain factual inaccuracies, stemming from their dependence on the parametric knowledge they encapsulate. To avoid such inaccuracies, also known as hallucinations, people use domain-specific knowledge (expertise) to support LLMs in the corresponding task, but the necessary knowledge engineering process usually requires considerable manual effort from experts. In this paper, we developed an approach to leverage the collective strengths of multiple agents to automatically facilitate the knowledge engineering process and then use the learned knowledge and Retrieval Augmented Generation (RAG) pipelines to optimize the performance of LLMs in domain-specific tasks. Through this approach, we effectively build AI assistants based on particular customized knowledge to help students better carry out personalized adaptive learning in digital transformation. Our initial tests demonstrated that integrating a Knowledge Graph (KG) within a RAG framework significantly improved the quality of domain-specific outputs generated by the LLMs. The results also revealed performance fluctuations for LLMs across varying contexts, underscoring the critical need for domain-specific knowledge support to enhance AI-driven adaptive learning systems.
8
Balasubramanian, Abhinav. « Accelerating Research with Automated Literature Reviews : A Rag-Based Framework ». International Journal of Multidisciplinary Research and Growth Evaluation. 6, no 2 (2025) : 337–42. https://doi.org/10.54660/.ijmrge.2025.6.2.337-342.
Texte intégralRésumé :
The exponential growth of academic publications has significantly increased the complexity of synthesizing knowledge across various disciplines. Researchers often struggle to manually analyze vast volumes of literature, a process that is both time-consuming and prone to biases. These challenges highlight the urgent need for innovative solutions that can streamline the literature review process and improve the quality of knowledge synthesis. This paper proposes a theoretical framework based on Retrieval-Augmented Generation (RAG) to automate the aggregation and summarization of academic literature. By integrating semantic search, generative AI, and knowledge graph technology, the framework offers a comprehensive solution to efficiently retrieve, synthesize, and contextualize key findings from relevant academic works. The use of knowledge graphs enhances the identification of research trends and gaps, offering researchers a deeper understanding of interconnected topics and areas requiring further exploration. Key contributions of this work include the conceptualization of the RAG-based framework and the introduction of a theoretical evaluation methodology. The evaluation metrics focus on semantic relevance, contextual coherence, source diversity, and usability, providing a robust foundation for assessing the framework’s potential. By reducing the time and effort required for literature reviews, this framework aims to accelerate innovation, facilitate interdisciplinary collaboration, and transform traditional research workflows.
9
Yang, Jiawei, Chuanyao Sun, Junwu Zhou, Qingkai Wang, Kanghui Zhang et Tao Song. « Knowledge-Inference-Based Intelligent Decision Making for Nonferrous Metal Mineral-Processing Flowsheet Design ». Minerals 15, no 4 (3 avril 2025) : 374. https://doi.org/10.3390/min15040374.
Texte intégralRésumé :
With the increasing diversification of ore types and the complexity of processing techniques in the mining industry, traditional decision-making methods for mineral processing flowsheets can no longer meet the high efficiency and intelligence requirements. This paper proposes a knowledge graph-based framework for constructing a mineral-processing design knowledge base and knowledge reasoning, aiming at providing intelligent and efficient decision support for mining engineers. This framework integrates Chinese NLP models for text vectorization, optimizes prompt generation through Retrieval Augmented Generation (RAG) technology, realizes knowledge graph construction, and implements knowledge reasoning for nonferrous metal mineral-processing design using large reasoning models. By analyzing the genetic characteristics of ores and the requirements of processing techniques, the framework outputs reasonable flowsheet designs, which could help engineers save research time and labor in optimizing processes, selecting suitable reagents, and adjusting process parameters. Through decision analysis of the mineral-processing flowsheets for three typical copper mines, the framework demonstrates its advantages in improving process flowsheet design, and shows good potential for further application in complex mineral-processing environments.
10
VanGundy, Braxton, Nipa Phojanamongkolkij, Barclay Brown, Ramana Polavarapu et Joshua Bonner. « Requirement Discovery Using Embedded Knowledge Graph with ChatGPT ». INCOSE International Symposium 34, no 1 (juillet 2024) : 2011–27. http://dx.doi.org/10.1002/iis2.13253.
Texte intégralRésumé :
AbstractThe field of Advanced Air Mobility (AAM) is witnessing a transformation with innovations such as electric aircraft and increasingly automated airspace operations. Within AAM, the Urban Air Mobility (UAM) concept focuses on providing air‐taxi services in densely populated urban areas. This research introduces the utilization of Large Language Models (LLMs), such as OpenAI's GPT‐4, to enhance the UAM Requirement discovery process.This study explores two distinct approaches to leverage LLMs in the context of UAM Requirement discovery. The first approach evaluates the LLM's ability to provide responses without relying on additional outside systems, such as a relational or graph database. Instead, a vector store provides relevant information to the LLM based on the user's question, a process known as Retrieval Augmented Generation (RAG). The second approach integrates the LLM with a graph database. The LLM acts as an intermediary between the user and the graph database, translating user questions into cypher queries for the database and database responses into human‐readable answers for the user. Our team implemented and tested both solutions to analyze requirements within a UAM dataset. This paper will talk about our approaches, implementations, and findings related to both approaches.
Thèses sur le sujet "Knowledge Graph-based Retrieval Augmented Generation (KG-RAG)"
1
Schaeffer, Marion. « Towards efficient Knowledge Graph-based Retrieval Augmented Generation for conversational agents ». Electronic Thesis or Diss., Normandie, 2025. http://www.theses.fr/2025NORMIR06.
Texte intégralRésumé :
Les agents conversationnels se sont largement répandus ces dernières années. Aujourd'hui, ils ont dépassé leur objectif initial de simuler une conversation avec un programme informatique et sont désormais des outils précieux pour accéder à l'information et effectuer diverses tâches, allant du service client à l'assistance personnelle. Avec l'essor des modèles génératifs et des grands modèles de langage (LLM), les capacités des agents conversationnels ont été décuplées. Cependant, ils sont désormais sujets à des hallucinations, générant ainsi des informations erronées. Une technique populaire pour limiter le risque d'hallucinations est la génération augmentée par récupération (RAG), qui permet d'injecter des connaissances lors de la génération de texte. Ces connaissances peuvent être extraites de graphes de connaissances (KG), qui sont des représentations structurées et accessibles pour les systèmes informatiques. Ainsi, nous explorons les architectures de KG-RAG pour construire des agents conversationnels de confiance. Nous démontrons l'intérêt de notre approche pour un cas d'usage réel de support citoyen·ne en construisant un agent conversationnel traitant les mesures autour du handicap dans des villes françaises. Nous présentons d'abord un historique des agents conversationnels, en introduisant les méthodes mises en œuvre au fil des années et les techniques d'évaluation. Nous définissons ensuite les KG et les ontologies, et explorons les techniques de construction et d'évaluation. Ne trouvant pas de KG directement exploitable, notre première contribution introduit OLAF : Ontology Learning Applied Framework. Ce système modulaire est conçu pour une construction automatisée et reproductible de KG à partir de textes non structurés. OLAF intègre des techniques linguistiques, statistiques et basées sur des LLM pour générer des ontologies minimales viables sur des domaines spécifiques. Appliqué à des ensembles de données réels, OLAF démontre des performances robustes grâce à des évaluations basées sur des ontologies de référence et des questions de compétence spécifiques à une tâche. Nous détaillons le processus de construction d'un KG sur la thématique du handicap dans une ville française. Nous proposons ensuite une architecture pour les systèmes de KG-RAG afin d'améliorer la recherche d'information en alignant les requêtes des utilisateur·rice·s avec les structures des graphes via la liaison d'entités, les patrons de requêtes et les méthodes de récupération basées sur les LLM. Nous démontrons l'intérêt de notre architecture sur différents cas d'utilisation, que nous évaluons selon des critères tels que la performance, les préférences humaines et l'impact environnemental. Bien que les préférences des utilisateur·rice·s avantagent l'architecture de Text-RAG, l'impact environnemental réduit de l'architecture de KG-RAG souligne son potentiel pour des pratiques d'IA durables. Enfin, nous identifions comme élément clé de l'architecture la partie concernant la recherche d'information. Nous abordons donc cette tâche dans notre architecture en explorant les techniques de vectorisation dans divers contextes, c'est-à-dire en améliorant la liaison d'entités, la recherche des données contextuelles et en fournissant un système de cache. Nous proposons également des mécanismes pour gérer les conversations multi-tours. Ce travail établit un cadre complet pour les systèmes de KG-RAG, combinant la sémantique des KG avec les capacités génératives des LLM pour construire des agents conversationnels précis, spécialisés et durables. Les contributions incluent OLAF pour une construction automatisée de KG, un pipeline de KG-RAG robuste, et des améliorations basées sur des représentations vectorielles pour la précision de la recherche d'information et la qualité des interactions. En répondant aux défis industriels des agents conversationnels, ces travaux posent les bases du déploiement de systèmes de KG-RAG dans des domaines spécialisés et variésConversational agents have become widespread in recent years. Today, they have transcended their initial purpose of simulating a conversation with a computer program and are now valuable tools for accessing information and carrying out various tasks, from customer service to personal assistance. With the rise of text-generative models and Large Language Models (LLMs), the capabilities of conversational agents have increased tenfold. However, they are now subject to hallucinations, producing false information. A popular technique to limit the risk of hallucinations is Retrieval Augmented Generation (RAG), which injects knowledge into a text generation process. Such injected knowledge can be drawn from Knowledge Graphs (KGs), which are structured machine-readable knowledge representations. Therefore, we explore Knowledge Graph-based Retrieval Augmented Generation (KG-RAG) to build trusted conversational agents. We demonstrate our approach on a real-world use case for citizen support by building conversational agents for disability management in cities. We first present a history of conversational agents, introducing the approaches implemented over the years and the evaluation techniques. We then define KGs and ontologies, and explore construction and evaluation techniques. As we could not find a directly exploitable KG, our first contribution introduces the Ontology Learning Applied Framework (OLAF). This modular system is built for automated and repeatable KG construction from unstructured text. OLAF integrates linguistic, statistical, and LLM-based techniques to generate Minimum Viable Ontologies for specific domains. Applied to real-world datasets, OLAF demonstrates robust performance through gold-standard evaluations and task-specific Competency Questions. We detail the construction process for a KG about disability management in a French city. We then propose an architecture for KG-RAG systems to enhance information retrieval by aligning user queries with KG structures through entity linking, graph queries, and LLM-based retrieval approaches. We demonstrate our architecture on different use cases, which we evaluate using criteria such as performance, human preference, and environmental impact. While user preferences advantage Text-RAG, KG-RAG's reduced computational footprint underscores its potential for sustainable AI practices. Finally, we identify the critical part of the architecture as the retriever. Therefore, we tackle the retrieval task in our architecture by exploring embeddings in various contexts, i.e. improving EL, retrieval, and providing a caching system. We also propose mechanisms for handling multi-turn conversations. This work establishes a comprehensive framework for KG-RAG systems, combining the semantic depth of KGs with the generative capabilities of LLMs to deliver accurate, contextual, and sustainable conversational agents. Contributions include OLAF for scalable KG construction, a robust KG-RAG pipeline, and embedding-based enhancements for retrieval and interaction quality. By addressing conversational agents' industrial challenges, such as scalability, retrieval precision, and conversational coherence, this research lays the foundation for deploying KG-RAG systems in diverse and specialised domains
Chapitres de livres sur le sujet "Knowledge Graph-based Retrieval Augmented Generation (KG-RAG)"
1
Malakhov, Kyrylo. « From Archimate to Computer Ontologies : Advancing Semantic Enterprise Architecture With RAG/RIG AI Services in RDF/OWL ». Dans Digital Transformation and Intelligent Systems : Theory, Models, Practice, 57–111. Iowa State University Digital Press, 2025. https://doi.org/10.31274/isudp.2025.197.02.
Texte intégralRésumé :
As modern AI-driven applications evolve, enterprise architecture (EA) must adapt to accommodate sophisticated text-processing services like Retrieval-Augmented Generation (RAG) and Retrieval-Interleaved Generation (RIG). Traditional modeling notations such as ArchiMate excel at describing business, application, and technology layers, but they can prove restrictive for dynamic, machine-readable contexts. This article explores how to combine ArchiMate’s well-structured EA views with an ontology-based paradigm in RDF/OWL, enabling more flexible, data-centric models. By representing RAG/RIG components–along with their knowledge bases, orchestrators, and compliance requirements–as semantic concepts, architects gain the ability to perform automated reasoning, enforce constraints (e.g., cardinalities, policies), and integrate real-time operational data. The approach transforms enterprise architecture from static diagrams into a living knowledge graph, supporting advanced SPARQL queries, iterative refinements in CI/CD pipelines, and richer collaboration across business and IT domains. Ultimately, the semantic web paradigm offers organizations a pathway to a truly adaptive and governed architecture that keeps pace with emerging AI capabilities.
2
Ilyas, Qazi Mudassar, et Sadia Aziz. « Enhancing the RAG Pipeline Through Advanced Optimization Techniques ». Dans Advances in Computational Intelligence and Robotics, 59–80. IGI Global, 2025. https://doi.org/10.4018/979-8-3693-6255-6.ch003.
Texte intégralRésumé :
Large language models produce excellent outputs for queries highly relevant to their training data. Retrieval-augmented generation (RAG) is used to augment this training data with additional contextual information based on additional data. Although RAG improves text generation through context retrieval from this additional data, the basic RAG system has limitations in chunking, hallucinations, and reliance on augmented content for knowledge-intensive tasks. This chapter discusses several advanced techniques to enhance retrieval and generation tasks in an RAG pipeline. The chapter discusses advanced strategies for chunking, vectorization, and search processes. Moreover, reranking, filtering, query transformation, query routing, and response synthesis improve generated responses' relevance, coherence, and accuracy.
3
Shi, Yunxiao, Xing Zi, Zijing Shi, Haimin Zhang, Qiang Wu et Min Xu. « Enhancing Retrieval and Managing Retrieval : A Four-Module Synergy for Improved Quality and Efficiency in RAG Systems ». Dans Frontiers in Artificial Intelligence and Applications. IOS Press, 2024. http://dx.doi.org/10.3233/faia240748.
Texte intégralRésumé :
Retrieval-augmented generation (RAG) techniques leverage the in-context learning capabilities of large language models (LLMs) to produce more accurate and relevant responses. Originating from the simple ‘retrieve-then-read’ approach, the RAG framework has evolved into a highly flexible and modular paradigm. A critical component, the Query Rewriter module, enhances knowledge retrieval by generating a search-friendly query. This method aligns input questions more closely with the knowledge base. Our research identifies opportunities to enhance the Query Rewriter module to Query Rewriter+ by generating multiple queries to overcome the Information Plateaus associated with a single query and by rewriting questions to eliminate Ambiguity, thereby clarifying the underlying intent. We also find that current RAG systems exhibit issues with Irrelevant Knowledge; to overcome this, we propose the Knowledge Filter. These two modules are both based on the instruction-tuned Gemma-2B model, which together enhance response quality. The final identified issue is Redundant Retrieval; we introduce the Memory Knowledge Reservoir and the Retriever Trigger to solve this. The former supports the dynamic expansion of the RAG system’s knowledge base in a parameter-free manner, while the latter optimizes the cost for accessing external knowledge, thereby improving resource utilization and response efficiency. These four RAG modules synergistically improve the response quality and efficiency of the RAG system. The effectiveness of these modules has been validated through experiments and ablation studies across six common QA datasets. The source code can be accessed at https://github.com/Ancientshi/ERM4.
4
Gustafson, Jerry Ryan David, Gaganpreet Jhajj, Xiaokun Zhang et Fuhua Oscar Lin. « Enhancing Project-Based Learning With a GenAI Tool Based on Retrieval ». Dans Advances in Educational Marketing, Administration, and Leadership, 161–94. IGI Global, 2024. http://dx.doi.org/10.4018/979-8-3693-5443-8.ch006.
Texte intégralRésumé :
This chapter presents a novel GenAI tool, called PBL Support Chatbot, designed to support project-based learning (PBL) by integrating retrieval-augmented generation (RAG) and knowledge graphs (KGs). The aim is to address common challenges in PBL, such as project complexity and curriculum alignment. The tool provides students with real-time, adaptive support through a chatbot that assists in navigating PBL tasks. To illustrate its application, the authors introduce a scenario involving an introductory computer programming course where students develop a text-based adventure game. By offering personalized guidance, immediate feedback, and accurate answers to student inquiries, the tool aims to enhance critical thinking, learning outcomes, knowledge application, and student engagement in PBL environments. The initial prototype demonstrates the potential to improve the PBL learning experience. This underscores the capability of using RAG to create a dynamic, interactive learning environment that aligns with students' individual learning paths and educational goals.
5
Le, Nguyen-Khang, Dieu-Hien Nguyen et Le Minh Nguyen. « ANSPRE : Improving Question-Answering in Large Language Models with Answer-Prefix Generation ». Dans Frontiers in Artificial Intelligence and Applications. IOS Press, 2024. http://dx.doi.org/10.3233/faia240778.
Texte intégralRésumé :
Large language models (LLMs) and Retrieval-Augmented-Generation (RAG) show remarkable capabilities in Open-domain question-answering (ODQA). Despite the advancements, LLMs tend to generate verbose responses, of which only a small part is the answer phrase. Although the ability to produce the confidence score for the answer is essential when deploying LLMs in high-risk domains, sequence probabilities obtained from LLMs do not correlate well with the probabilities of correctness and thus fail to represent confidence scores. This study introduces Answer-prefix Generation (Anspre) to improve generation quality, allowing the LLMs to output answer phrases and produce highly reliable confidence scores. We guide the model in predicting the answer phrase using an answer prefix and design a ranking score that integrates parametric and non-parametric knowledge. The answer phrases and their corresponding scores enable Anspre to aggregate results from different documents and samplings to boost performance and produce confidence scores highly correlated with correctness. We show that Anspre can be applied to any LLM and present an approach called Self-Anspre to combine Anspre with Self-reflective RAG, a state-of-the-art framework based on reflection tokens. Empirical evaluation on popular ODQA benchmarks shows that Anspre and Self-Anspre significantly improve state-of-the-art LLMs and RAG frameworks. An in-depth analysis shows that confidence scores produced by Anspre are highly correlated to the likelihood of correctness.
6
Darwish, Dina. « Integration of LLMs in Smart Cities for Sustainable Energy Solutions ». Dans Revolutionizing Urban Development and Governance With Emerging Technologies, 405–30. IGI Global, 2025. https://doi.org/10.4018/979-8-3373-1375-7.ch014.
Texte intégralRésumé :
By enabling the quick expansion of urban areas and efficiently managing resources through sustainable and scalable innovations, smart cities are crucial components in the continuous pursuit of improving urban living standards. Smart city applications face multiple obstacles, one of which is the risk of sensitive data being exposed without authorization, due to the proliferation of new technologies such as the Internet of Things (IoT), big data analytics, fog computing, and edge computing. Thanks to their adaptability in natural language processing and other areas, large language models (LLMs) as Chatbots have garnered a lot of interest. Data collecting systems for LLM fine-tuning, LLM embedding of power system-specific tools, and a retrieval augmented generation (RAG)-based knowledge pool to improve LLM answers and LLMs in safety-critical use cases are important areas for future research initiatives. This chapter discusses how LLMs can lead to energy efficiency and sustainability in smart cities, by using literature review and case studies, as well as providing future directions.
Actes de conférences sur le sujet "Knowledge Graph-based Retrieval Augmented Generation (KG-RAG)"
1
Dong, Chenxi, Yimin Yuan, Kan Chen, Shupei Cheng et Chujie Wen. « How to Build an Adaptive AI Tutor for Any Course Using Knowledge Graph-Enhanced Retrieval-Augmented Generation (KG-RAG) ». Dans 2025 14th International Conference on Educational and Information Technology (ICEIT), 152–57. IEEE, 2025. https://doi.org/10.1109/iceit64364.2025.10975937.
Texte intégral
2
Chen, Qi, et Lin Ni. « TCM MLKG-RAG : Traditional Chinese Medicine Intelligent Diagnosis Based on Multi-Layer Knowledge Graph Retrieval-Augmented Generation ». Dans 2024 4th International Conference on Electronic Information Engineering and Computer Communication (EIECC), 958–62. IEEE, 2024. https://doi.org/10.1109/eiecc64539.2024.10929529.
Texte intégral
3
Xiao, Wei, Yu Liu, XiangLong Li, Feng Gao et JinGuang Gu. « TKG-RAG : A Retrieval-Augmented Generation Framework with Text-chunk Knowledge Graph ». Dans 2024 25th International Arab Conference on Information Technology (ACIT), 1–9. IEEE, 2024. https://doi.org/10.1109/acit62805.2024.10877117.
Texte intégral
4
Hou, Yingqi, Yichang Shao, Zhongyi Han et Zhirui Ye. « Construction and Application of Traffic Accident Knowledge Graph Based on LLM ». Dans 2024 International Conference on Smart Transportation Interdisciplinary Studies. 400 Commonwealth Drive, Warrendale, PA, United States : SAE International, 2025. https://doi.org/10.4271/2025-01-7139.
Texte intégralRésumé :
<div class="section abstract"><div class="htmlview paragraph">Records of traffic accidents contain a wealth of information regarding accident causes and consequences. It provides a valuable data foundation for accident analysis. The diversity and complexity of textual data pose significant challenges in knowledge extracting. Previous research primarily relies on Natural Language Processing (NLP) to extract knowledge from texts and uses knowledge graphs (KGs) to store information in a structured way. However, the process based on NLP typically necessitates extensive annotated datasets for model training, which is complex and time-consuming. Moreover, the application of traffic accident knowledge graphs by direct information querying within the graph requiring complex commands, which leads to poor interaction capabilities. In this study, we adapt an innovative approach integrates Large Language Models (LLMs) for the construction and application of a traffic accident knowledge graph. Based on the defined schema layer of the traffic accident knowledge graph, we employ LLMs to extract knowledge from accident records and refine the extraction process by using prompts and few-shot learning mechanism. To ensure the accuracy of the extracted result, we employ a dual verification method combines self-verification of LLMs with manual inspection. Then we visualize the knowledge by using Neo4j. Finally, we explore the application of KGs within the framework of Retrieval-Augmented Generation (RAG) and construct an intelligent question-answering system. The combination of LLMs and KGs facilitates a framework of semi-automated knowledge extraction and analysis. The Knowledge Graph-Based Retrieval-Augmented Generation Question Answering System for Traffic Accidents enables complex query and answering tasks such as causation analysis and scenario generation for autonomous driving tests. The integration of KGs and LLMs not only expands the application scenarios of KGs but also reduces the risk of hallucination in responses generated by LLMs. This method efficiently Extracting information from unstructured textual data, advances the digitalization and intelligence of traffic accident management.</div></div>
5
Zhao, Ruilin, Feng Zhao, Long Wang, Xianzhi Wang et Guandong Xu. « KG-CoT : Chain-of-Thought Prompting of Large Language Models over Knowledge Graphs for Knowledge-Aware Question Answering ». Dans Thirty-Third International Joint Conference on Artificial Intelligence {IJCAI-24}. California : International Joint Conferences on Artificial Intelligence Organization, 2024. http://dx.doi.org/10.24963/ijcai.2024/734.
Texte intégralRésumé :
Large language models (LLMs) encounter challenges such as hallucination and factual errors in knowledge-intensive tasks. One the one hand, LLMs sometimes struggle to generate reliable answers based on the black-box parametric knowledge, due to the lack of responsible knowledge. Moreover, fragmented knowledge facts extracted by knowledge retrievers fail to provide explicit and coherent reasoning paths for improving LLM reasoning. To address these challenges, we propose KG-CoT, a novel knowledge-augmented paradigm that leverages a small-scale step-by-step graph reasoning model to reason over knowledge graphs (KGs) and utilizes a reasoning path generation method to generate chains of reasoning with high confidence for large-scale LLMs. Extensive experiments demonstrate that our KG-CoT significantly improves the performance of LLMs on knowledge-intensive question answering tasks, such as multi-hop, single-hop, and open-domain question answering benchmarks, without fine-tuning LLMs. KG-CoT outperforms the CoT prompting as well as prior retrieval-augmented and knowledge base question answering baselines. Moreover, KG-CoT can reduce the number of API calls and cost and generalize to various LLM backbones in a lightweight plug-and-play manner.
6
Kuratomi, Gustavo, Paulo Pirozelli, Fabio G. Cozman et Sarajane M. Peres. « A RAG-Based Institutional Assistant ». Dans Encontro Nacional de Inteligência Artificial e Computacional, 755–66. Sociedade Brasileira de Computação - SBC, 2024. https://doi.org/10.5753/eniac.2024.245243.
Texte intégralRésumé :
Although large language models (LLMs) demonstrate strong text generation capabilities, they struggle in scenarios requiring access to structured knowledge bases or specific documents, limiting their effectiveness in knowledge-intensive tasks. To address this limitation, retrieval-augmented generation (RAG) models have been developed, enabling generative models to incorporate relevant document fragments into their inputs. In this paper, we design and evaluate a RAG-based virtual assistant specifically tailored for the University of São Paulo. Our system architecture comprises two key modules: a retriever and a generative model. We experiment with different types of models for both components, adjusting hyperparameters such as chunk size and the number of retrieved documents. Our optimal retriever model achieves a Top-5 accuracy of 30%, while our most effective generative model scores 22.04% against ground truth answers. Notably, when the correct document chunks are supplied to the LLMs, accuracy significantly improves to 54.02%, an increase of over 30 percentage points. Conversely, without contextual input, performance declines to 13.68%. These findings highlight the critical role of database access in enhancing LLM performance. They also reveal the limitations of current semantic search methods in accurately identifying relevant documents and underscore the ongoing challenges LLMs face in generating precise responses.
7
Rai, P., A. Jain et A. Anand. « Generative AI and Large Language Model Assisted Causal Discovery and Inference for Driving Process Improvements ». Dans ADIPEC. SPE, 2024. http://dx.doi.org/10.2118/221872-ms.
Texte intégralRésumé :
Data-driven process management coupled with machine learning have been successful in driving commercial value to oil and gas operators by offering insights into process disruptions and their root causes. One frequently used approach is to analyze causes of process disruptions exclusively from historical data. In general, specific insights in the form of high correlation between certain process performance indicators and a well-defined measure of production inefficiency is often confounded as responsible causal factors. While this may yield some insights, the complexity of processes, measured in terms of number of entities involved and their interrelationships, requires a more nuanced approach that must include the context of the specific process. Thus, data analysis must be augmented with significant inputs from experts. Causal Inference provides a conceptual framework and tools for doing such analysis. In causal analysis, we embed this specific knowledge of subject matter experts using causal graphs consisting of process features (nodes) and their dependency (directed edges). For complex processes however, constructing causal graphs could be non-trivial due to ambiguity over which nodes to include and the plausible direction of their relationships. With the advent of foundational Large Language Models (LLM), there is an opportunity to mitigate this problem by utilizing the enormous information it encodes. Tools and technologies now exist to customize the response of LLM using retrieval of information from a corpus of specific high-quality knowledge in the form of related literature and data. It can therefore be used to assist the domain expert in building and finetuning the causal graph, and in simpler cases, can completely automate this step. In this work, we propose a two-step approach to combine the power of LLMs and Causal Analysis for analyzing inefficiencies in production processes. In the first step, we implement a Retrieval Augmented Generation (RAG) enhanced LLM prompting on a curated dataset designed to answer specific questions on relationship between process performance indicators. The outcome of this step is a directed acyclic graph encoding dependency of process performance indicators. Domain experts can validate or potentially refine the LLM-generated causal graph based on their domain knowledge for eliminating spurious hallucinations. In the second step, we use an appropriate causal inference method on the refined causal diagram and historical production data to estimate the causal effect of process variable contributing to disruptions or inefficiencies. Thus, by combining human expertise with machine learning, this framework offers a comprehensive approach for optimizing production processes.
8
Schönwälder, Erik, Martin Hahmann et Gritt Ott. « Using compact Retrieval-Augmented Generation for knowledge preservation in SMBs ». Dans 13th International Conference on Human Interaction & Emerging Technologies : Artificial Intelligence & Future Applications. AHFE International, 2025. https://doi.org/10.54941/ahfe1005891.
Texte intégralRésumé :
Knowledge preservation is a critical challenge for small and medium-sized businesses (SMBs). Employee fluctuation and evolving work tasks create a permanent risk of knowledge and experience loss. Therefore, SMBs need effective and efficient strategies for knowledge retention. As most knowledge in companies is primarily encoded as language or text, large language models (LLMs) offer a promising solution for the preservation and utilization of knowledge. However, despite their strengths, their adoption and deployment are challenging. To address this issue, we propose a system based on the Retrieval-Augmented Generation (RAG) concept that combines small, locally run language models with traditional retrieval algorithms to significantly enhance the process of knowledge preservation and utilization by reducing search efforts.
9
Danter, Daniel, Heidrun Mühle et Andreas Stöckl. « Advanced Chunking and Search Methods for Improved Retrieval-Augmented Generation (RAG) System Performance in E-Learning ». Dans 2024 AHFE International Conference on Human Factors in Design, Engineering, and Computing (AHFE 2024 Hawaii Edition). AHFE International, 2024. http://dx.doi.org/10.54941/ahfe1005756.
Texte intégralRésumé :
Our study evaluates different search methodologies—Hybrid Search and Semantic Search—within a Retrieval-Augmented Generation (RAG) framework specifically for E-Learning. The primary objective is to enhance the accuracy and efficiency of using Large Language Models (LLMs), such as GPT-4, by employing advanced Prompt Engineering Techniques in E-Learning environments. Efficient search and chunking methods are critical for optimizing the quality of answers provided by these systems.To achieve this, we utilized the RAGas testing framework, focusing on performance parameters including Answer Correctness, Context Recall, Context Precision, Faithfulness, and Answer Relevancy. In our implementation, documents were divided into text chunks and indexed in a database using both vector and keyword indexing. This allowed for searches by vectors for similar records and keyword searches for exact matches. These records were then incorporated into prompts as context to improve LLM responses. The AI model used for generating embeddings, such as OpenAI's text-embedding-ada-002, plays a crucial role in this process by creating high-dimensional representations that capture deep semantic meanings.Current retrieval methods, like keyword and similarity-based searches, often fall short due to limitations in chunk quality, which directly impacts the accuracy of the RAG system. This study aims to improve the retriever component and, consequently, the overall accuracy of the RAG system by comparing three different chunking methods and two search approaches. We conducted tests using 57 questions across multiple files under various configurations.This research examines different search methods, including Hybrid Search, which integrates traditional keyword search with semantic search in order to provide more accurate and contextually relevant results. In comparison, Semantic Search utilizes deep learning models to comprehend the context and meaning of search queries and documents, thereby providing more precise information retrieval. The analysis also compared different chunking methods, such as Recursive Chunking, which divides text into hierarchical sections that are further subdivided until the desired granularity is reached. BERT Chunking utilizes the BERT model to segment text, taking semantic meaning into account to ensure coherent chunks. Token Chunking segments text based on individual tokens, offering fine-grained control over segmentation.Our results, evaluated using the RAGas testing framework, highlight the strengths and weaknesses of each search method and chunking technique. This study provides valuable insights into optimizing RAG Systems for E-Learning through advanced Prompt Engineering Techniques, aiming to improve knowledge transfer regarding efficiency and accuracy.
10
Zhang, Leo, et Carlos Gonzalez. « An AI-Driven Debate Judging System using Emotional and Content Analysisbased on Artificial Intelligence and Machine Learning ». Dans 9th International Conference on Artificial Intelligence, Soft Computing And Applications, 217–30. Academy & Industry Research Collaboration, 2025. https://doi.org/10.5121/csit.2025.150419.
Texte intégralRésumé :
Evaluating debates is a challenging task requiring nuanced understanding of abstract reasoning. Current AI systems struggle with these complexities, often providing shallow or biased feedback. To address this, we developed Blitz Debate, a Retrieval-Augmented Generation (RAG) system that combines large language models (LLMs) with semantic search capabilities [1][2]. Blitz Debate retrieves relevant external knowledge to evaluate debate arguments with depth and accuracy, offering structured, real-time feedback. Our experiments demonstrated 90.5% accuracy in identifying winners and superior interpretative responses compared to vanilla ChatGPT, highlighting its ability to provide evidence-based and nuanced analysis. Challenges included limited real-time reasoning and contextual depth, which we addressed through enhanced context modeling and adaptive argument generation. By offering scalable, unbiased, and context-aware feedback, Blitz Debate makes debate evaluation more effective and accessible, fostering critical thinking and argumentation skills for students, educators, and competitive debaters alike.