Search Results (104)

Reliable retrieval-augmented generation requires consistency across query interpretation, evidence selection, and final answer generation. This study defines computational symmetry as bidirectional coverage among canonical query constraints, traceable evidence, and answer claims, with residual asymmetry triggering correction or abstention. The proposed framework integrates a source-linked raw text/entity/event knowledge graph, hybrid dense–sparse retrieval, cross-encoder reranking, pre-retrieval semantic alignment, and a post-retrieval verification gate. DeepSeek-V3 serves as the implementation backbone, while “ChatGPT-type” denotes the broader class of instruction-following conversational large language models. Experiments use T2Ranking for retrieval and reranking, ATIS for diagnostic intent–slot evaluation, and controlled dialogue scenarios derived from T2Ranking. The hierarchical representation improves retrieval F1 from 0.586 to 0.660, while the complete pipeline increases average answer correctness from 0.530 to 0.611 compared with direct LLM answering and from 0.559 to 0.611 compared with graph retrieval. On ATIS, the controller achieves 92.61% intent accuracy, below Joint BERT at 95.18%, and is therefore treated as a reusable orchestration module rather than a superior classifier. The results support the proposed verification correction framework within the tested settings, without claiming superiority over untested adaptive RAG systems. Full article

Retrieval-augmented generation (RAG) is increasingly deployed in safety-critical cybersecurity question answering, where an answer must be both factually correct and faithful to its sources. Evaluation in this space routinely conflates the two, treating grounding as a proxy for correctness. We show that this conflation is unsafe. We introduce SENTINEL-QA, a bilingual English and Macedonian cybersecurity QA benchmark of 70 hand-authored items over a curated corpus of authoritative source documents, and use it to compare four answer generation pipelines (zero-shot, Classic RAG, DSPy-structured RAG, and GraphRAG) across three generators, judged by a four-model LLM panel on both factual correctness and grounding. The two metrics decouple under graph-based retrieval augmentation: on all three generators our chunk-similarity GraphRAG makes answers look better sourced without making them more correct, and as the retrieval budget grows it can even degrade factual correctness while grounding holds steady. Structured, minimal prompting improves both qualities, at lower latency and cost; a four-cell ablation attributes the factual gain to pruning the instruction, while the declarative schema contributes on grounding. The judge panel mirrors the split, agreeing more on what is well grounded than on what is true, under absolute as well as rank-based agreement criteria. We conclude that grounding alone is an insufficient target for RAG evaluation and that pruning the instruction, rather than expanding retrieval, is what improves factual correctness, without eliminating the grounded-but-wrong regime. Full article

Large Language Models (LLMs) show considerable potential for materials-science question answering. However, LLM responses may still be affected by unsupported parametric associations, while dense Retrieval-Augmented Generation (RAG) can fragment relational evidence across text chunks. Moreover, general graph-based retrieval does not necessarily preserve the hierarchical relations and factual attributes required to resolve implicit material constraints. To address these limitations, we propose MCTD-KG, a multi-source heterogeneous knowledge graph integrated with a Knowledge-Enhanced RAG framework for complex material question answering. MCTD-KG adopts a Classification–Term–Data ontology to connect disciplinary taxonomies, domain concepts, semantic relations, and empirical records from toolbooks and the scientific literature. Through LLM-assisted knowledge extraction, entity normalization, and multi-source integration, the resulting graph contains more than 530,000 entities across three layers, including 61,768 text-extracted Term-layer entities. During inference, Dual-Channel Retrieval jointly retrieves query-relevant relational paths and associated material attributes, while an explicit semantic filtering stage screens candidate evidence against the query constraints. Evaluation on an expert-validated benchmark of 1577 questions shows that the proposed framework achieves an overall accuracy of 68.48%, compared with 17.40% for the zero-shot Pure LLM, 24.79% for the best Vanilla RAG setting, and 44.96% for GraphRAG. It also achieves 45.22% accuracy on four-hop questions, compared with 39.49% for GraphRAG. These results indicate that integrating multi-source domain knowledge with relation-preserved retrieval and attribute-supported filtering provides more focused and inspectable evidence, thereby supporting more accurate complex material question answering. Full article

In critical infrastructure environments, cybersecurity situation-awareness platforms generate large volumes of alerts, including substantial numbers of false positives, placing a considerable burden on security analysts. At present, alert correlation methods mainly rely on rule-based matching or statistical clustering, and large language models often lack the domain-specific threat intelligence required for reliable security analysis. This paper proposes GRAL, which is an AI-driven framework that combines graph neural networks (GNN) for cross-asset temporal alert correlation, retrieval-augmented generation (RAG) for dynamic threat intelligence enrichment, and large language models (LLM) for semantic reasoning and verdict generation. A temporal heterogeneous graph attention network constructs alert-relation graphs within a 72 h sliding window, and temporal decay and multi-relational dependencies are captured. Powered by bge-m3 embeddings and a dense vector index, the RAG module retrieves the most relevant threat intelligence entries above a cosine similarity threshold of 0.75. A domain-specific dataset of 1000 annotated security alerts from a nuclear power operational environment was built, and Cohen’s Kappa reached 0.87. The experiments show that GRAL achieves a macro-averaged precision of 87.0%, a macro-averaged recall of 97.0%, and a binary false-positive rate of 9.1%, together with 92.5% alert compression. Generalisation capability is confirmed by cross-dataset evaluation on CICIDS2017 (93.0% accuracy and 92.5% F1-score) and UNSW-NB15 (89.4% accuracy and 89.8% F1-score). Full article

Text-to-Cypher generator systems translate natural language questions into Cypher queries, enabling intuitive interactions with graph databases such as Neo4j and Amazon Neptune. Despite recent advancements in LLM-based Cypher query generation, the vulnerabilities of the known methods—such as prompt injection attacks—are not discussed in detail. In this paper, we employ a robust Retrieval-Augmented Generation (RAG) architecture tailored specifically for text-to-Cypher tasks, leveraging dense vector retrieval to enhance query generation accuracy. We propose a dynamic and self-corrective procedure with feedback-loop-based AI architecture with Large Language Models (LLMs) for near real-time validation and correction of generated queries. We create a systematic procedure for generating datasets specifically designed to assess prompt injection robustness. Comprehensive evaluations are conducted using a diverse set of LLMs, including GPT-4o, DeepSeek R1, Claude 3.5 Sonnet and Qwen 2.5 Coder 32B Instruct. Our evaluation results indicate substantial improvements in resiliency against prompt injection attacks compared to various benchmarks. It is demonstrated that the proposed solution outperforms various training-free prompt injection defense methods. Full article

High-temperature creep data for aero-engine fasteners are essential for life assessment and structural safety, but such records are often archived as heterogeneous tables, reports and figures with weak cross-record associations. This study develops a traceable knowledge-graph retrieval-augmented generation (KG-RAG) workflow for internal GH2132 fastener creep data. Seventeen GH2132 creep specimens with different geometries were organized into a standardized document archive, parsed into source-linked table and text fragments, and converted into structured entities and relationships. Iterative prompt templates were used to check extraction completeness, repair missing fields and preserve provenance without fine-tuning the underlying language model. The resulting Neo4j knowledge graph links material, specimen geometry, service condition, creep measurement and source evidence, while LightRAG retrieves vector chunks, entity contexts and relationship contexts through round-robin merging. The system was evaluated using 20 seed-engineering questions across five retrieval modes (Naive RAG, Local, Global, Hybrid and Mix), yielding 100 query-evaluation records. The questions covered simple, comparative, multi-constraint, out-of-knowledge-base and ambiguous queries. Mix achieved the strongest RAGAS profile, with answer correctness, answer similarity, answer relevancy, context precision, context recall and faithfulness scores of 0.85, 0.83, 0.79, 0.88, 0.87 and 0.85, respectively. Hybrid may be more practical for routine queries, although this qualitative interpretation was not supported by systematic latency benchmarking. A separate assessment by 15 domain experts gave a weighted score of 94/100. These results show that a source-linked KG-RAG workflow can improve the reuse, grounding and auditability of heterogeneous creep records within a bounded engineering dataset. Full article

Large Language Models (LLMs) have significant potential in regulated domains such as law, healthcare, and compliance, where users need help interpreting complex rules and documents. However, these domains also make the risks of Large Language Models especially serious: a system may hallucinate legal authority, rely on outdated rules, mix jurisdictions, or expose sensitive information. Retrieval-Augmented Generation (RAG) reduces these risks by grounding the model’s answer in a curated document corpus, but standard RAG still does not guarantee that the retrieved sources are legally valid, up to date, applicable to the correct jurisdiction, or safe to use. In this paper, we present an ontology-governed approach to legal RAG. The central idea is to use a legal ontology not merely as background knowledge, but as an active control layer. Before retrieval, the ontology filters legal sources by jurisdiction, topic, lifecycle status, and temporal validity. After generation, validation rules check whether the answer is supported by approved evidence, cites valid legal sources, respects jurisdictional boundaries, and avoids unsafe or privacy-violating content. The system also records retrieval, validation, and response-generation steps in an audit trail to support later review. In this way, the proposed Legal Rule Auditor extends Graph RAG from a retrieval-enhancement technique into a governance architecture for legal question answering. Its goal is not simply to improve answer relevance, but to ensure that answers are legally grounded, trusted, current, jurisdictionally appropriate, and traceable. Full article

This paper examines how semantic information architectures within technical communication shape topic ensemble properties being relevant for retrieval-augmented generation (RAG) systems. They allow for investigating the AI-readiness of technical content for AI-based delivery in the present domain of water treatment. The analysis characterizes the dependence of AI-driven delivery on similarity-based metrics and metadata completeness. Topic content management is operationalized within the PI-Class framework by analyzing topics with respect to content variants and versioning, and by assessing their implications for retrieval precision. Building on previous research in technical communication, the paper further investigates the role of large language models (LLMs) in supporting the content engineering phase through automated analysis of legacy documents, derivation of metadata classifications, and curation of the resulting semantic structures in knowledge graphs. Full article

Retrieval-augmented generation (RAG) has been widely used to improve factual grounding in small language models (SLMs). However, many existing retrieval methods rely mainly on shallow semantic similarity between queries and text chunks. As a result, the retrieved evidence is often fragmented or weakly connected, which can limit multi-hop reasoning and sometimes lead to hallucinated answers. In this work, we propose Hallucination-Aware Multi-Objective Ant Colony Optimization (HA-MOACO), a structure-aware Graph-RAG framework that models relationships between pieces of evidence and searches for useful reasoning paths in a graph structure. The framework first constructs a domain knowledge graph and identifies several candidate entry nodes related to the query. Starting from these nodes, an ant colony optimization (ACO) strategy is used to explore possible evidence paths. During this process, multiple signals are considered simultaneously, including semantic relevance, structural connectivity between nodes, and reliability indicators that help reduce contradictory or low-confidence evidence. The selected evidence paths are then used to build a compact and grounded context for the language model. This process helps keep important reasoning connections while reducing the influence of irrelevant information. Experimental results on reasoning-focused benchmarks show that the proposed framework improves answer accuracy by about 6%, increases F1 by roughly 5–6%, and improves exact-match scores by around 7% compared with strong graph-based retrieval baselines. At the same time, the hallucination rate is reduced by about 40%, while retrieval latency is roughly 20% lower. These results suggest that combining structure-aware retrieval with reliability-oriented optimization can improve both reasoning quality and factual consistency in SLMs, while still remaining efficient for practical deployment. Full article

Retrieval-Augmented Generation (RAG) grounds large language models in external evidence, but many RAG systems represent knowledge either as flat text chunks or as automatically constructed indexing graphs. This assumption is incomplete for curated thematic corpora, including religious scriptures, legal codes, clinical guidelines, educational taxonomies, policy documents, and library classification systems, where domain experts have already organized knowledge into thematic paths and citeable canonical units. This paper investigates how RAG can exploit such expert-authored structures while pruning evidence to a compact and query-specific set. We conduct a critical survey supported by a bibliometric analysis of 2815 Scopus-indexed RAG-related records exported on 26 May 2026, of which 2809 records were retained after duplicate removal. The bibliometric results indicate rapid growth in RAG research but limited explicit consolidation around curated thematic paths, canonical evidence units, or thematic path-guided evidence pruning. We therefore propose ThemePath-RAG, a retrieval framework that retrieves curated thematic paths as high-recall semantic routes, expands candidate canonical evidence, and applies query-aware scoring and global pruning before generation. To assess operational feasibility, we implement ThemePath-RAG for Qur’anic question answering and compare it with a Vector RAG baseline on 150 paired questions using RAGAS context relevance with gpt-4o-mini as the LLM evaluator. Both methods return approximately three final ayat per question. Vector RAG achieves higher mean context relevance than ThemePath-RAG ($0.920$ versus $0.798$; $p<0.001$). Thus, the proof of concept establishes the feasibility of thematic-path-guided retrieval and identifies evidence-selection challenges, rather than demonstrating superiority over conventional vector retrieval. The paper clarifies the framework’s relationship to GraphRAG, LightRAG, HippoRAG, PathRAG, ontology-based RAG, and AI-augmented bibliometric systems, and outlines a language-matched, multi-baseline evaluation agenda for future cross-domain validation. Full article

Hundreds of connected components expose vehicle systems to an increasing number of cyber attacks. Vehicle manufacturers must establish the most appropriate procedures for vulnerability assessment and penetration testing using a mix of proprietary solutions and open-source standards. The spread of Large Language Models (LLMs) simplifies the interaction between automotive experts and domain-specific knowledge bases. While proprietary LLM services can be expensive and raise data privacy concerns, open-source LLMs are potentially more cost-effective and better suited to in-house solutions. However, the effectiveness of open-source models in retrieving automotive-related cybersecurity information remains unclear. While adopting open-source LLMs with a few billion parameters, their reasoning and generative capabilities under in-context learning settings are questionable. To bridge this gap, this paper explores efficient solutions for Retrieval-Augmented Generation (RAG) architecture for automotive cybersecurity relying on open-source LLMs. The ultimate goal is to enable cost-effective retrieval and question answering from in-domain knowledge bases, overcoming the privacy and confidentiality issues raised by automotive experts. Using a Graph Knowledge Base designed for a corporate scenario, this paper first defines an expert-curated testing benchmark to evaluate in-domain question-answering performance across multiple aspects. Next, it proposes different RAG system variants based on various retrieval strategies and LLMs, both proprietary and open-source. Finally, it quantitatively evaluates the effectiveness of the content retrieval strategies and compares the pertinence, conciseness, and completeness of generated answers through human validation. Notably, within the scope of the performed analysis, RAGs that rely on open-source models demonstrate promising and competitive performance in some respects compared to the OpenAI GPT model. RAG retrieval performance also surpasses that of state-of-the-art solutions on existing cybersecurity benchmarks (Recall@K above 0.95 vs. 0.65 for state-of-the-art in-domain RAGs). Full article

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. Traditional fusion methods often fail to bridge the semantic gap between low-level sensing signals and high-level manufacturing cognition, limiting intelligent anomaly analysis and decision-making capability. To address this issue, this paper proposes a semantic translation and fusion framework for industrial heterogeneous data based on Knowledge Graph (KG), Retrieval-Augmented Generation (RAG), and Large Language Models (LLMs). First, a unified semantic translation mechanism is developed to convert multimodal industrial data into structured semantic representations for cross-modal alignment. Second, an industrial knowledge graph and RAG mechanism are introduced to integrate process knowledge, maintenance manuals, and historical fault records into the reasoning process. Third, an LLM-driven reasoning framework is designed for multimodal semantic fusion, anomaly identification, causal analysis, and optimization recommendation generation. In addition, a digital twin-based visualization interface is constructed to realize real-time interaction between production lines, industrial data, and intelligent cognitive reports. Experimental results demonstrate that the proposed framework significantly improves industrial reasoning accuracy, anomaly analysis correctness, and response efficiency compared with general-purpose LLMs, providing an effective solution for intelligent cognition and decision-making in discrete manufacturing systems. Full article

The European Green Deal (EGD) is the European Union’s comprehensive growth strategy for achieving climate neutrality by 2050. It comprises 17 interrelated policy documents, spanning sectors from energy and transport to biodiversity and sustainable finance. Despite their collective importance, these documents are characterized by significant heterogeneity in structure, terminology, and scope, making it challenging for non-technical stakeholders to navigate, cross-reference, extract, and validate information across their corpus as a whole. Considering the limitations of Natural Language Processing (NLP) approaches targeting the accessibility of policy documents and the lack of prior work explicitly focusing on the EGD and sustainability, we introduce a graph retrieval-augmented generation (GraphRAG) pipeline for natural language question answering (QA) over the EGD corpus. Our contributions include the conceptualization of a generalizable entity type set for policy documents for the EGD and its representation in the form of a knowledge graph, the development of two novel graph-based retrieval strategies that exploit the pre-computed structural properties of the knowledge graph, and the release of a specialized evaluation dataset, built on persona profiles matching real-world user profiles. The implementation and evaluation of the proposed approach are detailed, highlighting its effectiveness for the analysis of policy documents for the EGD against other GraphRAG baselines. Full article

Aligning industrial technological demands with academic expertise is critical for effective technology transfer. However, existing Expert Recommendation Systems (ERS) are frequently hindered by a “semantic gap” arising from terminological discrepancies between industry and academia, alongside a reliance on rigid classification taxonomies. To address these limitations, this paper proposes an automated expert finding framework that integrates Large Language Models (LLMs) with a hierarchical Retrieval-Augmented Generation (RAG) mechanism. Initially, we employ LLMs for the unsupervised extraction of research domains and technical keywords from heterogeneous multi-source data. To mitigate terminological diversity, we introduce a vector clustering-based Semantic Normalization module. By mapping diverse keyword variants into unified “Concept Clusters,” this module reduces vocabulary sparsity by 98%. These organized clusters are structured into a “Semantic Tree” to support a hierarchical RAG strategy, enabling a coarse-to-fine retrieval process from broad disciplinary domains down to specific technical achievements. In this paper, RAG refers to a retrieval-augmented expert recommendation workflow, in which the retrieved achievements and expert evidence are used as grounded context for generating an explanatory recommendation report. Evaluations on a real-world dataset show that the framework achieves a Precision@5 of 78.4% and a Recall@10 of 81.2%, outperforming flat vector retrieval baselines by over 20% in precision. Furthermore, hierarchical domain pruning significantly reduces computational overhead, decreasing average query latency by a factor of three (to 115.8 ms). These results demonstrate that the proposed system effectively bridges the industry–academia semantic gap, providing a scalable and accurate solution for expert recommendation. Full article

Conversational search systems (CSSs) are emerging as a transformative interface for health information seeking, enabling multi-round, natural language interactions that integrate diverse medical resources. This scoping review synthesizes evidence on the capabilities, limitations, applications, and future directions of CSSs in healthcare. Following PRISMA-ScR guidelines, we systematically searched multidisciplinary databases (2010–2025), screened 3789 records, and included 325 studies addressing CSSs in health contexts. Analysis identified six thematic domains: (1) capabilities and limitations, (2) enhancement methods, (3) clinical applications, (4) trust, user experience, and interaction design, (5) readability, health literacy, and patient communication, and (6) cross-lingual and domain-specific adaptation. Findings show CSSs offer advantages in personalization, structured output, and patient education, but face challenges in accuracy, timeliness, and semantic consistency, particularly in high-risk clinical decision-making. Enhancement strategies such as retrieval-augmented generation (RAG), knowledge graphs (KG), fine-tuning, and composite approaches improve performance, while trust-building requires transparency, empathy, and ethical safeguards. Cross-lingual disparities and cultural adaptability remain critical gaps. Overall, CSSs hold substantial potential to improve health information access and literacy, but safe, equitable, and culturally sensitive integration demands multidimensional optimization in knowledge updating, bias control, and interaction design, alongside clinician oversight, to ensure reliability and maximize public health impact. Full article