Search Results (741)

Large Language Models (LLMs) exhibit remarkable generative capabilities but remain vulnerable to hallucinations—outputs that are fluent yet inaccurate, ungrounded, or inconsistent with source material. To address the lack of methodologically grounded surveys, this paper introduces a novel method-oriented taxonomy of hallucination mitigation strategies in text-based LLMs. The taxonomy organizes over 300 studies into six principled categories: Training and Learning Approaches, Architectural Modifications, Input/Prompt Optimization, Post-Generation Quality Control, Interpretability and Diagnostic Methods, and Agent-Based Orchestration. Beyond mapping the field, we identify persistent challenges such as the absence of standardized evaluation benchmarks, attribution difficulties in multi-method systems, and the fragility of retrieval-based methods when sources are noisy or outdated. We also highlight emerging directions, including knowledge-grounded fine-tuning and hybrid retrieval–generation pipelines integrated with self-reflective reasoning agents. This taxonomy provides a methodological framework for advancing reliable, context-sensitive LLM deployment in high-stakes domains such as healthcare, law, and defense. Full article

This study introduces a Large Language Model (LLM)-based framework that combines drug combination data with a knowledge graph to predict synergistic oncology drug combinations with mechanistic insights. Using a retrieval-augmented generation (RAG) approach, over 50,000 in vitro drug pair assay results and 1631 human clinical trial and preclinical test entries were integrated to enhance predictive accuracy and explainability. Validation achieved an F1 score of 0.80, demonstrating the framework’s potential to streamline drug discovery and improve translational strategies in cancer treatment. Full article

In recent years, the convenience and potential for information extraction offered by Remote Sensing Image–Text Retrieval (RSITR) have made it a significant focus of research in remote sensing (RS) knowledge services. Current mainstream methods for RSITR generally align fused image features at multiple scales with textual features, primarily focusing on the local information of RS images while neglecting potential semantic information. This results in insufficient alignment in the cross-modal semantic space. To overcome this limitation, we propose a Multi-Scale Semantic-Aware Remote Sensing Image–Text Retrieval method (MSSA). This method introduces Progressive Spatial Channel Joint Attention (PSCJA), which enhances the expressive capability of multi-scale image features through Window-Region-Global Progressive Attention (WRGPA) and Segmented Channel Attention (SCA). Additionally, the Image-Guided Text Attention (IGTA) mechanism dynamically adjust textual attention weights based on visual context. Furthermore, the Cross-Modal Semantic Extraction Module (CMSE) incorporated learnable semantic tokens at each scale, enabling attention interaction between multi-scale features of different modalities and the capturing of hierarchical semantic associations. This multi-scale semantic-guided retrieval method ensures cross-modal semantic consistency, significantly improving the accuracy of cross-modal retrieval in RS. MSSA demonstrates superior retrieval accuracy in experiments across three baseline datasets, achieving a new state-of-the-art performance. Full article

Large Language Models (LLMs) encounter significant challenges when applied in specialized domains that require precise and localized information. This problem is particularly critical in regulatory sectors, such as the animal health sector in Brazil, where professionals depend on complex and constantly updated legal norms to perform their work. The generic knowledge encapsulated in traditional LLMs is often insufficient to provide reliable support in these contexts, which can lead to inaccurate or outdated responses. To address this gap, this work presents a practical implementation of a Retrieval-Augmented Generation (RAG) system. We detail the integration of this system with the Plataforma de Defesa Sanitária Animal do Rio Grande do Sul (PDSA-RS), a real platform used for animal production certification. Our solution connects an LLM to an external knowledge base containing specific Brazilian legislation, allowing the model to retrieve relevant legal texts in real time to generate its responses. The principal objective is to demonstrate how this approach can produce accurate and contextually grounded answers for professionals in the veterinary field, assisting in decision-making processes for sanitary certification. Full article

Recipes available on the web often lack nutritional transparency and clear indicators of dietary suitability. While searching by title is straightforward, exploring recipes that meet combined dietary needs, nutritional goals, and ingredient-level preferences remains challenging. Most existing recipe search systems do not effectively support flexible multi-dietary reasoning in combination with user preferences and restrictions. For example, users may seek gluten-free and dairy-free dinners with suitable substitutions, or compound goals such as vegan and low-fat desserts. Recent systematic reviews report that most food recommender systems are content-based and often non-personalized, with limited support for dietary restrictions, ingredient-level exclusions, and multi-criteria nutrition goals. This paper introduces DietQA, an end-to-end, language-adaptable chatbot system that integrates a Knowledge Graph (KG), Retrieval-Augmented Generation (RAG), and a Large Language Model (LLM) to support personalized, dietary-aware recipe search and question answering. DietQA crawls Greek-language recipe websites to extract structured information such as titles, ingredients, and quantities. Nutritional values are calculated using validated food composition databases, and dietary tags are inferred automatically based on ingredient composition. All information is stored in a Neo4j-based knowledge graph, enabling flexible querying via Cypher. Users interact with the system through a natural language chatbot friendly interface, where they can express preferences for ingredients, nutrients, dishes, and diets, and filter recipes based on multiple factors such as ingredient availability, exclusions, and nutritional goals. DietQA supports multi-diet recipe search by retrieving both compliant recipes and those adaptable via ingredient substitutions, explaining how each result aligns with user preferences and constraints. An LLM extracts intents and entities from user queries to support rule-based Cypher retrieval, while the RAG pipeline generates contextualized responses using the user query and preferences, retrieved recipes, statistical summaries, and substitution logic. The system integrates real-time updates of recipe and nutritional data, supporting up-to-date, relevant, and personalized recommendations. It is designed for language-adaptable deployment and has been developed and evaluated using Greek-language content. DietQA provides a scalable framework for transparent and adaptive dietary recommendation systems powered by conversational AI. Full article

Inverse problems are ubiquitous across many scientific fields, and involve the determination of the causes or parameters of a system from observations of its effects or outputs. These problems have been deeply studied through the use of simulated data, thereby under the lens of simulation-based inference. Recently, the natural combination of Continuous Normalizing Flows (CNFs) and Flow Matching Posterior Estimation (FMPE) has emerged as a novel, powerful, and scalable posterior estimator, capable of inferring the distribution of free parameters in a significantly reduced computational time compared to conventional techniques. While CNFs provide substantial flexibility in designing machine learning solutions, modeling decisions during their implementation can strongly influence predictive performance. To the best of our knowledge, no prior work has systematically analyzed how such modeling choices affect the robustness of posterior estimates in this framework. The aim of this work is to address this research gap by investigating the sensitivity of CNFs trained with FMPE under different modeling decisions, including data preprocessing, noise conditioning, and noisy observations. As a case study, we consider atmospheric retrieval of exoplanets and perform an extensive experimental campaign on the Ariel Data Challenge 2023 dataset. Through a comprehensive posterior evaluation framework, we demonstrate that (i) Z-score normalization outperforms min–max scaling across tasks; (ii) noise conditioning improves accuracy, coverage, and uncertainty estimation; and (iii) noisy observations significantly degrade predictive performance, thus underscoring reduced robustness under the assumed noise conditions. Full article

This study presents a domain-adapted retrieval-augmented generation (RAG) pipeline that integrates geological knowledge with large language models (LLMs) to support intelligent question answering in the metallogenic domain. Focusing on the Qin–Hang metallogenic belt in South China, we construct a bilingual question-answering (QA) corpus derived from 615 authoritative geological publications, covering topics such as regional tectonics, ore-forming processes, structural evolution, and mineral resources. Using the ChatGLM3-6B language model and LangChain framework, we embed the corpus into a semantic vector database via Sentence-BERT and FAISS, enabling dynamic retrieval and grounded response generation. The RAG-enhanced model significantly outperforms baseline LLMs—including ChatGPT-4, Bing, and Gemini—in a comparative evaluation using BLEU, precision, recall, and F1 metrics, achieving an F1 score of 0.8689. The approach demonstrates high domain adaptability and reproducibility. All datasets and codes are openly released to facilitate application in other metallogenic belts. This work illustrates the potential of LLM-based knowledge engineering to support digital geoscientific research and smart mining. Full article

Background: Speech loss is recognised as one of the most devastating outcomes for individuals with ALS, yet active speech intervention is rarely targeted in this population. Clinicians face significant challenges in managing dysarthria associated with ALS due to the rapidly progressive nature of the disease, historical concerns around intensive exercise accelerating decline, and an absence of direction on restorative and compensatory intervention strategies in current clinical care guidelines. This review evaluates the scope and quality of evidence for speech treatments in ALS to identify knowledge gaps and establish research priorities to guide clinical care. Methods: Studies were retrieved from six electronic databases (PubMed, CINAHL, Embase, Cochrane library, Web of Science, and PsycINFO). Results: Four studies met inclusion criteria. Treatment approaches included: music-based speech therapy; multisubsystem speech rehabilitation program, tongue strengthening and articulation training; and Lee Silverman Voice Treatment-LOUD^® combined with additional voice and articulation therapy. Sample sizes were small, with all studies demonstrating notable methodological weaknesses. The limited evidence base, marked by conflicting results and methodological flaws, prevents any reliable conclusions about treatment effectiveness. Conclusions: Despite the prevalence and impact of dysarthria in this population, evidence for speech treatment remains sparse, of generally low quality, and provides limited guidance for clinical practice. The changing perspective on exercise in ALS warrants rigorous investigation of tailored dysarthria interventions for this population that are minimally fatiguing and enhance speech by making use of residual physiologic support. Full article

Accurate calculation of embodied carbon emissions in buildings (ECE) is crucial to achieving global carbon neutrality. However, fragmented data, inconsistent regional standards, and low computational efficiency have long hindered existing methods. This study innovatively integrates large language models (LLMs) with retrieval-enhanced generation (RAG) technology to establish a new intelligent accounting paradigm for embodied carbon in buildings. Through a systematic evaluation of three basic models—Kimi, Doubao, and DeepSeek-R1—in a five-level progressive input scenario, the study quantitatively reveals the “information sensitivity” patterns of LLMs. To address the illusion errors of general models in professional scenarios, an innovative three-stage closed-loop architecture of “knowledge retrieval—calculation embedding—trustworthy generation” is proposed. By dynamically invoking domain knowledge bases and embedded computing modules, zero-error verification of benchmark data is achieved. The core contributions include the following: (1) It has been clarified that the basic large model has application potential in calculating the implicit carbon emissions of buildings, but the reliability of the results is limited. (2) The influence of data elements on calculation accuracy is revealed. (3) The application path for integrating RAG with large models has been pioneered, and the results show that the RAG technology can enhance the performance of large models in calculating the implicit carbon emissions of buildings by approximately 25%. (4) The significant efficiency improvement of RAG technology is verified. (5) A supporting theoretical and application system is established. Full article

Existing Retrieval-Augmented Generation (RAG) systems face challenges in enterprise settings due to limited retrieval scope and data security risks. When relevant internal documents are unavailable, the system struggles to generate accurate and complete responses. Additionally, using closed-source Large Language Models (LLMs) raises concerns about exposing proprietary information. To address these issues, we propose the Secure Multifaceted-RAG (SecMulti-RAG) framework, which retrieves not only from internal documents but also from two supplementary sources: pre-generated expert knowledge for anticipated queries and on-demand external LLM-generated knowledge. To mitigate security risks, we adopt a local open-source generator and selectively utilize external LLMs only when prompts are deemed safe by a filtering mechanism. This approach enhances completeness, prevents data leakage, and reduces costs. In our evaluation on a report generation task in the automotive industry, SecMulti-RAG significantly outperforms traditional RAG—achieving 79.3–91.9% win rates across correctness, richness, and helpfulness in LLM-based evaluation and 56.3–70.4% in human evaluation. This highlights SecMulti-RAG as a practical and secure solution for enterprise RAG. Full article

The numerous inhabited small islands of the Mediterranean basin are marginal geographic territories of high natural value. Historically, island communities have developed complex, poly-cultural agricultural systems, based on the use of native genetic resources and traditional ecological knowledge, to address the challenges linked to unfavorable climate, geology, and topography. However, economic, socio-demographic, and climatic factors have caused farmland abandonment, leading to soil and land degradation and to a decline in biodiversity and ecosystem services. Following the PRISMA guidelines, we conducted a systematic review to assess the state of scientific research with regard to agriculture on small Mediterranean islands. After screening records retrieved on Scopus, Web of Science, CABI, and Google Scholar, 167 articles published before July 2025 were included in the analysis. The articles covered 6 countries and 126 islands, with Greek and Italian islands being the most represented. Key topics included trajectories, drivers, and consequences of land use change, agrobiodiversity, and water resources. To complete the systematic review, 30 relevant EU-funded projects were identified and analyzed. Overall, the scientific research aimed at supporting agriculture on Mediterranean small islands tends to focus on a single issue or very few issues. However, we suggest that given the complexity of the drivers and consequences of farmland abandonment, more integrated approaches could have a greater impact. By providing a systematic overview of the current state of the research on agriculture on small Mediterranean islands, this review offers a solid basis for guiding ongoing and future research, actions, and policies aimed at building resilience in these fragile and endangered lands. Full article

This paper introduces GraphTrace, a novel retrieval framework that integrates a domain-specific knowledge graph (KG) with a large language model (LLM) to improve information retrieval for complex, multi-hop queries. Built on structured economic data related to the COVID-19 pandemic, GraphTrace adopts a modular architecture comprising entity extraction, path finding, query decomposition, semantic path ranking, and context aggregation, followed by LLM-based answer generation. GraphTrace is compared against baseline retrieval-augmented generation (RAG) and graph-based RAG (GraphRAG) approaches in both retrieval and generation settings. Experimental results show that GraphTrace consistently outperforms the baselines across evaluation metrics, particularly in handling mid-complexity (5–6-hop) queries and achieving top scores in directness during the generation evaluation. These gains are attributed to GraphTrace’s alignment of semantic reasoning with structured KG traversal, combining modular components for more targeted and interpretable retrieval. Full article

Query reformulation techniques optimize user queries to better align with documents, thus improving the performance of Information Retrieval (IR) systems. Previous methods have primarily focused on query expansion using techniques such as synonym replacement to improve recall. With the rapid advancement of Large Language Models (LLMs), the knowledge embedded within these models has grown. Research in prompt engineering has introduced various methods, with prompt chaining proving particularly effective for complex tasks. Directly prompting LLMs to reformulate queries has become a viable approach. However, existing LLM-based prompt methods for query reformulation often introduce irrelevant content into reformulated queries, resulting in decreased retrieval precision and misalignment with user intent. We propose a novel approach called Hierarchical Prompt Chaining for Query Reformulation (HiPC-QR). HiPC-QR employs a two-step prompt chaining technique to extract keywords from the original query and refine its structure by filtering out non-essential keywords based on the user’s query intent. This process reduces the query’s restrictiveness while simultaneously expanding essential keywords to enhance retrieval effectiveness. We evaluated the effectiveness of HiPC-QR on two benchmark retrieval datasets, namely MS MARCO and TREC Deep Learning.The experimental results show that HiPC-QR outperforms existing query reformulation methods on large-scale datasets in terms of both recall@10 and MRR@10. Full article

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating external knowledge retrieval to improve factual consistency and reduce hallucinations. Despite growing interest, its use in healthcare remains fragmented. This paper presents a Systematic Literature Review (SLR) following PRISMA guidelines, synthesizing 30 peer-reviewed studies on RAG in clinical domains, focusing on three of its most prevalent and promising applications in diagnostic support, electronic health record (EHR) summarization, and medical question answering. We synthesize the existing architectural variants (naïve, advanced, and modular) and examine their deployment across these applications. Persistent challenges are identified, including retrieval noise (irrelevant or low-quality retrieved information), domain shift (performance degradation when models are applied to data distributions different from their training set), generation latency, and limited explainability. Evaluation strategies are compared using both standard metrics and clinical-specific metrics, FactScore, RadGraph-F1, and MED-F1, which are particularly critical for ensuring factual accuracy, medical validity, and clinical relevance. This synthesis offers a domain-focused perspective to guide researchers, healthcare providers, and policymakers in developing reliable, interpretable, and clinically aligned AI systems, laying the groundwork for future innovation in RAG-based healthcare solutions. Full article

Hospital design plays a pivotal role in improving patient outcomes, enhancing clinical efficiency, and strengthening infection control. Since the outbreak of COVID-19, research in this field has expanded significantly, showing a marked trend toward interdisciplinary integration. In this study, bibliometric analysis was conducted using CiteSpace (version 6.2.R3) as the primary tool, with Excel and Tableau (version 2024.3) as supplementary software. A total of 877 documents on hospital design published between 1932 and 2025 were retrieved from the Web of Science Core Collection and analyzed from multiple perspectives. The analysis examined publication trends, collaborative networks, co-citation structures, disciplinary evolution, and keyword dynamics. The results indicate that the field has entered a phase of rapid development since 2019. Global collaboration networks are becoming increasingly multipolar; yet, institutional and author-level connections remain decentralized, with relatively low overall density. Evidence-based design (EBD) continues to serve as the theoretical foundation of the field, while emerging themes such as healing environments, biophilic design, and patient-centered spatial strategies have become major research hotspots. Increasingly, the field reflects deeper integration across disciplines, including architecture, medicine, nursing, and environmental science. This study provides a clearer picture of the developmental trajectory, knowledge base, and future directions of hospital design research, offering systematic insights and theoretical guidance for both scholars and practitioners. Full article