Search Results (582)

The rapid progress of large language models (LLMs) has fostered the development of domain-specific variants in law, medicine, and finance. However, existing legal LLMs still struggle to generate contextually grounded and regulation-compliant responses in complex scenarios of fair competition review. To address this, we present FairAgent, a collaborative multi-agent framework that unifies data refinement and reinforcement learning for legal reasoning. FairAgent integrates two core modules: (1) EchoCourt, a closed-loop data generation and refinement pipeline that constructs high-quality question–answer pairs through generation, critique, and optimization guided by a hierarchical Fairness Knowledge Forest; and (2) a two-stage outcome-based reinforcement learning mechanism that progressively teaches the model to invoke and integrate external retrieval in reasoning. We further enhance learning stability through a RAG-based rollout and retrieval-mask loss. Extensive evaluations demonstrate that FairAgent significantly improves reasoning accuracy, interpretability, and compliance in fair competition review compared with state-of-the-art baselines, establishing a scalable framework for retrieval-augmented legal intelligence. Full article

This paper presents how an ontology-based Knowledge Graph (KG) for basketball box scores can be exploited to support several real use cases, and also presents competency questions, including sports analytics, complex question answering and data browsing with semantic filters. To illustrate this, we present the BBall ontology, the modeling decisions and the key advantages of creating a KG based on this ontology. Then, we introduce a KG covering 25 seasons of the EuroLeague and more than 5 million triples, and we showcase the functionality of three research prototypes based on that KG, particularly a faceted search application with semantic filters and two text-to-SPARQL applications leveraging LLMs, including support for multilingual queries. The first LLM-based application enables SPARQL query editing, and the second is a chat-based application offering interactive dialogue between the user and the system. For these applications, we describe their functionality and approach, and we compare them (along with a classical SPARQL query editor) in several dimensions. Finally, we provide the statistics for the constructed KG, indicative SPARQL queries addressing the competency questions, results and error analysis for the text-to-SPARQL method, efficiency results, and a historical analysis showing the evolution of several factors of EuroLeague basketball from 2000 to 2025. Full article

Background: This study aims to examine the level of awareness, attitudes (including stigma and discrimination), and behaviors related to tuberculosis among the population of the Republic of Kazakhstan to identify priorities for raising awareness and reducing stigma. Methods: The study interviewed 2400 people from six regions of Kazakhstan using stratified random sampling based on gender and age. Respondents were chosen from cities and villages, including RK citizens over 18 who could answer questions. Additionally, 400 people with HIV, 200 drug users, 200 internal migrants, and 500 health workers were interviewed. Recruitment was done through profile organizations and the snowball method, with all participants giving informed consent. Results: The study showed different levels of knowledge about tuberculosis (TB) in Kazakhstan. Radiography was the most commonly known detection method (71–91%). Awareness of sputum testing was highest among drug users (84%) and HIV patients (77%), but lower among internal migrants (39%). Internal migrants had the most uncertainty about TB tests (17%). Stigmatizing views of TB patients existed, with 28–38% believing most people reject them. Among healthcare workers, only 38. 8% correctly identified the G-Xpert test for TB and rifampicin resistance, and over one-third misunderstood the Mantoux test’s purpose. Conclusions: The findings show a need for focused educational efforts to boost TB awareness and lessen stigma, especially among internal migrants and the general public. Vulnerable groups, like PLHIV and PWUD, have higher awareness but still encounter major barriers. Improving healthcare workers’ knowledge about TB diagnostics is also crucial. Specific communication strategies and policies are needed to improve TB detection, reduce social stigma, and improve healthcare access for at-risk groups in Kazakhstan. Full article

Multi-hop question answering (MHQA) requires models to retrieve and reason over evidence distributed across multiple documents, which remains challenging for conventional retrieval-augmented generation (RAG) approaches. Although RAG improves factual grounding by incorporating external knowledge, flat retrieval strategies often struggle to maintain coherent reasoning chains when implicit dependencies among entities and documents are involved. This paper presents a query-driven dual-layer graph retrieval framework for MHQA. The framework operates on a unified heterogeneous graph integrating entities, relations, and supporting texts, and dynamically constructs candidate subgraphs through joint retrieval over entities and relations, complemented by lexical retrieval signals. Reasoning paths are refined by combining structural strength modeling with contrastive learning-based path scoring, and an adaptive pruning strategy is employed to regulate evidence scale according to query complexity and path score distributions. Experiments on HotpotQA and 2WikiMultihopQA show that the proposed framework achieves higher EM and F1 scores than existing RAG and graph-based retrieval methods, particularly in complex multi-hop scenarios. These results indicate the importance of structured and query-adaptive evidence organization for multi-hop reasoning. Full article

Background/Objectives: The use of over-the-counter vitamin D₃ supplements has increased substantially in recent years. Compared with pharmaceuticals, dietary supplements are subject to less stringent regulatory oversight, raising concerns regarding labeling accuracy, consumer knowledge, and patient safety. This study aimed to assess public knowledge and preferences related to vitamin D₃ supplementation and to evaluate the content accuracy and short-term stability of commonly used products. Methods: A cross-sectional online survey containing 39 questions was conducted in Hungary between 1 May and 30 June 2024. Based on survey responses, the most frequently used vitamin D₃ supplements (five soft gel capsules and four tablets) were selected for laboratory analysis. Vitamin D₃ content was quantified using a validated high-performance liquid chromatography (HPLC) method with UV detection. Soft gel capsules were additionally exposed to natural daylight for one month to assess short-term photostability. Results: In total, 367 participants (mean age 31.0 ± 12.5 years) completed the survey, and only 3.5% answered correctly all knowledge-based questions. Six commonly reported supplement brands accounted for approximately 90% of responses. Measured vitamin D₃ content remained within the tolerance limit (−20% to +50%). Following sunlight exposure, three of four capsule products showed no substantial vitamin D₃ loss, while one exhibited a 14.7% decrease. Conclusions: Most analyzed vitamin D₃ supplements complied with labeled content claims, but substantial knowledge gaps were identified that may affect patient safety. The validated HPLC method supports pharmacovigilance-oriented quality monitoring of vitamin D₃ supplements and underscores the need for improved professional counseling. Full article

Exposure to poor indoor air quality (IAQ) conditions represents a major public health concern, with adverse effects on human health and well-being. The adoption of innovative technological solutions can support timely risk awareness, enable informed decision-making, and ultimately mitigate this health burden. In this context, Large Language Models (LLMs) emerge as a promising technological avenue through the Retrieval-Augmented Generation (RAG) paradigm, which extends their inherent natural language understanding capabilities with explicit access to external knowledge bases, enabling evidence-grounded reasoning and informed recommendations. The present work introduces an integrated GraphRAG-based Question Answering (QA) system that couples a domain-specific knowledge graph encoding fundamental IAQ concepts and relationships with a RAG-based natural language interface, thereby enabling explainable, context-aware, and advanced analytical reasoning over IAQ data. The evaluation results demonstrate the effectiveness of the proposed QA system across both retrieval and generation stages. The retrieval mechanism achieved a context recall of 0.914 and a precision of 0.838, while the generation mechanism attained a faithfulness score of 0.906 and an answer relevancy score of 0.891. Full article

Knowledge graphs represent real-world facts as structured triplets and underpin a wide range of applications, including question answering, recommendation, and retrieval-augmented generation. Automatically extracting such triplets from unstructured text is essential for scalable knowledge base construction. Traditional extraction methods require task-specific training data and struggle to generalize across domains. Large language models (LLMs) offer an alternative through in-context learning, enabling flexible extraction without fine-tuning. However, LLMs frequently hallucinate—generating plausible triplets unsupported by the source text. The root cause is the lack of provenance: existing methods produce triplets without explicit links to their textual origins, making faithfulness unverifiable. This paper presents Anchor-Extraction-Verification-Supplement (AEVS), a framework that grounds every triplet element to the source text. AEVS operates in three stages: (1) anchor discovery identifies entities, relation phrases, and attribute values with precise positions, forming a constrained extraction vocabulary; (2) grounded extraction generates triplets linked to discovered anchors; and (3) restoration-based verification validates triplets through hierarchical matching, with a coverage-aware supplement ensuring comprehensive extraction. Experiments on WebNLG, REBEL, and Wiki-NRE demonstrate consistent improvements over both trained models and LLM-based baselines. Ablation studies confirm that anchor-based constraints are the primary mechanism for hallucination reduction. Dedicated analyses of anchor discovery quality, computational cost (2.83–4.28 LLM calls per sample), and hallucination rates (0.23–20.23% across model–dataset configurations) provide insights into the framework’s practical applicability and limitations. Full article

Surveys are important tools for collecting knowledge, including student knowledge, and assessing their opinions and behavior. Survey results inspire information processing and selection of a processing method for further knowledge management. In this study, an improved approach to presenting survey results was developed, utilizing a Likert scale. In the survey, 20 students answered 10 questions (issues) that examined their opinions on the impact of modern technical equipment on dairy production assessment. The feature significance index (FSI) was utilized to inform the development of the survey study results. The FSI is the ratio of the percentage share of the highest to the lowest ratings on a Likert scale. In the case of four issues, none of the students indicated the options had very little impact and little impact. Therefore, the FSI could not be calculated, so a modified version was proposed. After ranking the issues in the survey based on the FSI, the difference in FSI between the best-rated and worst-rated issues was more than 13 times. This difference was less than two times in the modified version of the FSI. A larger difference allows for a more comprehensive interpretation of the survey results. The study confirmed that the small number of survey participants is a key limitation in developing the survey results. Full article

Medical question answering (QA) systems and conversational agents have attracted growing interest as tools that can assist clinicians, support medical students, and help patients navigate complex information sources. However, existing evaluations of retrieval strategies largely overlook the cost–benefit balance—here referred to as frugality, under realistic computational constraints. This work introduces a frugality-based evaluation framework that jointly assesses accuracy improvements and computational cost to determine when retrieval-augmented generation is beneficial in medical question answering, rather than evaluating retrieval effectiveness through accuracy alone. This study addresses these gaps through a systematic comparative framework that evaluates retrieval relevance, computational efficiency, and knowledge base composition across multiple biomedical QA tasks. We employ open-source LLMs (LlaMA-3-8B-Instruct, Mistral-7B-Instruct-v0.3, and DeepSeek-7B-Chat) across three benchmark medical QA datasets, including MedMCQA, MedQA-USMLE, and PubMedQA. In addition to that, we evaluate a dataset with larger contexts to simulate model distraction across the CliniQG4QA dataset using additional models (Meditron-7B, Qwen2.5-7B-Medical, Medgemma-4B, Phi-3-mini-4k-Instruct, and GPT4o-Mini). We examine how retrieval design choices alter the accuracy–latency trade-off, examining how relevance, corpus design, and hardware constraints interact in medical retrieval-augmented generation (RAG) systems. Our comprehensive results demonstrate when retrieval is genuinely beneficial versus when it imposes unnecessary computational costs, highlighting interactions between relevance and corpus designs in QA. Full article

Large Language Models (LLMs) have achieved substantial progress in knowledge-intensive tasks, particularly through Retrieval-Augmented Generation (RAG) frameworks. However, existing RAG systems often suffer from performance degradation when input queries are misaligned with retrieval requirements, and effectively coordinating retrieval with reasoning remains challenging—especially for multi-hop questions requiring iterative retrieval steps. To address these challenges, we propose ReWriteGen, a unified framework that integrates query rewriting, retrieval augmentation, and complementary generation within a coordinated architecture, optimized using reinforcement learning (Group Relative Policy Optimization, GRPO) and Direct Preference Optimization (DPO). ReWriteGen introduces a retrieval-aware query rewriting mechanism to better align input queries with external knowledge. The framework optimizes retrieval-augmented answers without requiring supervised reasoning annotations.Our experiments show that ReWriteGen consistently outperforms traditional RAG baselines across three multi-hop QA benchmarks: HotpotQA, MuSiQue, and 2Wiki. On HotpotQA, ReWriteGen achieves improvements of 5.32 and 5.10 percentage points in EM and LLM-based evaluation, respectively, compared to the strongest baseline. Corresponding gains of 11.90 and 7.18 are observed on MuSiQue, and 15.45 and 18.60 on 2Wiki.ReWriteGen enhances the coordination between retrieval and reasoning in LLMs, delivering consistent performance gains while reducing reliance on supervised reasoning annotations and extensive task-specific engineering. Full article

Graph-enhanced Retrieval-Augmented Generation (RAG) frameworks, such as GraphRAG, improve large language model (LLM)-based question answering (QA) by constructing and leveraging structured, knowledge-condensed graph information. However, they still face challenges in complex multi-hop reasoning tasks and often incur substantial time and resource costs, resulting in low efficiency. To address these limitations, we propose DualGraphRAG, a dual-view graph-enhanced RAG framework designed to achieve both high QA performance and computational efficiency for complex reasoning over open-domain corpora. Specifically, DualGraphRAG constructs a knowledge graph (KG) by automatically extracting triples from unstructured text using LLMs, and embeds KG nodes with unified text embeddings. For each query, multiple types of KG nodes are generated through a dedicated query enhancement module. Based on these nodes, DualGraphRAG employs a dual-view retrieval strategy to retrieve both one-hop triples that capture local context and shortest paths that compress global connectivity information, thereby facilitating answer generation. Experimental results show that, compared with NaiveRAG, GraphRAG, and LightRAG, DualGraphRAG achieves the best or competitive performance on benchmark datasets and significantly improves efficiency. Overall, DualGraphRAG organizes and exploits KG information in a dual-view manner, leveraging triples and shortest paths to offer a reliable and efficient framework for open-domain QA with complex multi-hop reasoning. Full article

Background/Objectives: Large language models (LLMs) have shown promising results in medical decision support; however, their effectiveness in managing acute cholecystitis and other gallbladder diseases remains insufficiently examined. This study evaluated the performance of a neuro-symbolic LLM system that integrates multiple AI agents with neural–symbolic reasoning for acute cholecystitis management and compared its diagnostic accuracy with that of human expert physicians across three clinical specialties. Methods: This multi-center cross-sectional study included 30 case-based questions covering acute cholecystitis and gallbladder diseases, stratified across eight predefined disease categories: acute calculous cholecystitis (n = 6), acute acalculous cholecystitis (n = 2), complicated cholecystitis including gangrenous, emphysematous, and perforated variants (n = 5), chronic cholecystitis and biliary colic (n = 4), gallbladder polyps and adenomyomatosis (n = 3), Mirizzi syndrome (n = 2), gallbladder carcinoma (n = 4), and post-cholecystectomy complications (n = 4). Questions were categorized into diagnosis (n = 10), treatment (n = 10), and complications/prognosis (n = 10). Gold standard answers were established through consensus by an expert panel consisting of two senior general surgery expert clinicians and one senior emergency medicine expert clinician, each with more than 20 years of clinical experience, utilizing the Tokyo Guidelines 2018 (TG18) as the reference standard for diagnostic criteria, severity grading, and management recommendations. The expert panel achieved unanimous consensus on all 30 gold standard answers. All responses were cross-referenced against the primary TG18 publications to ensure guideline-based rather than solely opinion-based reference standards. This consensus-based, guideline-anchored approach is consistent with established methodologies for gold standard establishment in AI diagnostic accuracy studies. Performance of a neuro-symbolic LLM system orchestrated via LangGraph v1.0 was compared against 10 general surgery specialists, 10 emergency medicine physicians, and 10 gastroenterology specialists from four tertiary centers in Turkey. The neuro-symbolic system incorporated the Tokyo Guidelines 2018 (TG18) as its symbolic knowledge base for diagnostic criteria, severity grading, and management algorithms. Results: The neuro-symbolic system attained the highest overall accuracy rate of 96.7% (29/30), markedly surpassing the performance of general surgery specialists (average 82.3% ± 6.8%), emergency medicine physicians (average 71.0% ± 8.2%), and gastroenterology specialists (average 78.7% ± 7.4%). Furthermore, the neuro-symbolic system exhibited superior performance across all clinical categories. Among human participants, general surgeons showed the highest accuracy in treatment decisions (88.0%), while gastroenterologists excelled in diagnostic questions (82.0%). Emergency medicine physicians showed comparable performance to other specialties in acute presentation scenarios. ROC analysis revealed excellent discrimination for the neuro-symbolic system (AUC = 0.983) compared to general surgery (AUC = 0.856), gastroenterology (AUC = 0.821), and emergency medicine (AUC = 0.764). Conclusions: The neuro-symbolic LLM system exhibited superior performance in standardized guideline-concordant case-based assessment of acute cholecystitis management compared to all human expert groups, reflecting its consistent application of encoded guideline criteria. These findings support its potential role as a clinical decision-support tool that augments, rather than replaces, physician expertise. The system’s consistent application of standardized guidelines indicates its potential utility as a clinical decision support tool, particularly in settings where specialist expertise is limited. However, these results should be interpreted within the constraints of a structured case-based evaluation and do not imply global clinical superiority over human experts. Full article

Nature-based Solutions (NbS) have emerged as transformative approaches to address societal challenges, support biodiversity, and enhance human well-being. Globally, NbS are recognized for their potential to mitigate climate change impacts such as coastal flooding. Despite growing policy interest, limited empirical evidence exists on their real-world effectiveness, particularly in Africa. The core objective of this study was to evaluate how community perceptions, awareness, and demographic factors influence the acceptance and effectiveness of NbS for flood risk reduction in selected coastal communities of Rivers State, Nigeria. Specifically, it aimed to assess community perceptions and awareness of NbS, identify demographic, geographic, and psychosocial factors influencing these perceptions, and analyze how risk perception and local knowledge affect acceptance. The study addressed three key questions: (1) How do community perceptions affect NbS acceptance and implementation? (2) What factors shape awareness and understanding of NbS in Kula, Oyorokoto, and Bonny? (3) How do perceptions vary across demographic groups? To answer these, a structured survey of 1224 respondents was conducted: 61% were male and 39% female, with most aged 31–50 years (80%). Education emerged as a key factor—about 49% of respondents had at least secondary or post-secondary education, which showed a significant link with positive perceptions of NbS (χ² = 460.98, p < 0.001, Cramer’s V = 0.434). Occupation also shaped views: traders (36.8%) and fishers (24.5%) formed the majority, with occupational patterns showing moderate influence (χ² = 112.68, p < 0.001, Cramer’s V = 0.215). Overall, awareness was the strongest predictor, with communities reporting higher NbS awareness demonstrating significantly greater acceptance (OR = 0.06, p < 0.001). These findings highlight that targeted awareness-raising, education, and community engagement are critical to promoting mangrove conservation, afforestation, and ecosystem restoration, ultimately strengthening resilience to climate-induced risks in coastal communities. Full article

Traditional claim management relies heavily on manual analysis and expert judgment, resulting in inefficiencies, information omissions, and heightened risks of disputes. To address these challenges, this paper constructs a domain-specific ontology for construction engineering claims through a five-step process, organizing the relevant knowledge into five unified core classes. Based on this ontology, a knowledge graph is built and stored in Neo4j. The resulting knowledge graph-enhanced LLM question-answering system, evaluated using BLEU-4, BERT-Cosine similarity, ROUGE-1, and ROUGE-L metrics, demonstrates superior performance compared to both the base LLM and Vector RAG approaches. The results indicate that the proposed ontology effectively serves the purpose of knowledge sharing and reuse while providing practical support for construction claim management. Full article

Large language models (LLMs) with the Transformer architecture as the core have made significant progress in the field of natural language processing, and their application value in English teaching has also attracted much attention. In tasks such as text generation, question-answering systems, and translation, the processing capabilities of LLMs have significantly improved. However, existing LLMs have problems such as insufficient coverage of professional knowledge, rough semantic parsing, and weak personalized services. To address the aforementioned issues, this study proposes a dual-path retrieval-enhanced generation scheme that integrates vector databases and intelligent agents, aiming to improve the application of large models in English language teaching. Semantic retrieval of unstructured data in English teaching is realized through vector databases, knowledge is dynamically acquired by combining agents, and the accuracy is improved by using Bloom filters to fuse dual-path retrieval. At the same time, the retrieval efficiency is optimized by an importance-oriented algorithm, and user profiles are constructed based on multi-dimensional data to achieve personalized adaptation. Experiments show that the maximum optimization of the retrieval time of this scheme can reach 26.32%, and the highest retrieval accuracy can reach 86%. The key indicators and scores in tasks such as English knowledge retrieval and question-answering reasoning are better than those of the comparative schemes, providing an effective technical path for intelligent English teaching. Full article