Search Results (835)

Advances in Generative Artificial Intelligence have enabled the development of models capable of generating text, images, and audio that are similar to what humans can create. These models often have valuable general knowledge thanks to their training on large datasets. Through fine-tuning or prompt-based adaptation, this knowledge can be applied to specific tasks. In this work, we propose a modular approach to automated news generation using Large Language Models, composed of an information retrieval module and a text generation module. The proposed system leverages both publicly available (open-weight) and proprietary Large Language Models, enabling a comparative evaluation of their behavior within the proposed news generation pipeline. We describe the experiments carried out with a total of five representative Large Language Models spanning both categories, detailing their configurations and performance. The results demonstrate the feasibility of using Large Language Models to automate this task and identify systematic differences in behavior across model categories, as well as the problems that remain to be solved to enable fully autonomous news generation. Full article

Modern machine tools are safety-critical mechatronic systems, yet shop floor maintenance from abnormal events still relies heavily on scarce expert know-how and time-consuming manual searches across heterogeneous controller documentation. This paper presents an on-premise multimodal AI assistant. It integrates large language models with retrieval augmented generation and real-time machine signals to support operator-in-the-loop fault diagnosis. The proposed system provides three tightly coupled functions: (1) alarm-grounded guidance, which answers controller alarms and recommends corrective actions by grounding generation on manuals, maintenance procedures, and historical alarm cases; (2) parameter-aware reasoning, which injects live process and health indicators (e.g., spindle temperature, vibration, and axis states) into the reasoning context through an industrial data pipeline, enabling context specific troubleshooting; and (3) vision enabled support, which retrieves similar visual cases and generates concise visual instructions when text alone is insufficient. The assistant is deployed within an intranet environment to satisfy industrial security and privacy requirements and is orchestrated via lightweight tool calling for seamless integration with existing shop floor systems. Experiments on real machine tool alarm scenarios demonstrate that the proposed system achieves 82% answer correctness for alarm Q&A and improves response consistency and time-to-resolution compared with baseline keyword search and template-based guidance. The results suggest that grounded, multimodal chatbot assistants can act as practical AI-based feedback and decision support mechanisms for mechatronic production equipment, bridging human skill gaps while enhancing reliability and maintainability. Full article

Generative AI systems increasingly mediate how students retrieve literature and generate citations, shifting methodological rigor toward the maintenance of an auditable evidence trail. This study audits the search stage of AI-assisted literature review work, focusing on retrieval performance and citation traceability rather than downstream screening or synthesis. Four widely accessible tools were compared across two retrieval postures, and Boolean queries were executed against Scopus and evaluated against a DOI-verified librarian baseline built from Scopus, Web of Science, and Google Scholar. Using a canonical prompt and a bounded top-k capture rule (k = 20), each bibliographic record was evaluated for DOI traceability, DOI resolution integrity, metadata accuracy, and run-to-run drift. Records were screened through staged title/abstract and full-text eligibility review, and the final set included 37 studies after quality appraisal was 37 studies. Across sixteen audit runs, natural-language prompting frequently produced under-target yields, recurrent integrity failures, and low overlap with the librarian benchmark. Boolean translation improved run completion and increased the proportion of auditable records, but reproducibility remained unstable across repeated runs. These findings show that correctness at the record level does not ensure stability at the evidence-set level. Limitations include the bounded tool set, the search-stage focus, and the absence of downstream screening or synthesis evaluation. Retrieval posture, therefore, emerges as a practical governance lever for AI-assisted literature review workflows and supports the use of a student-facing verification checklist anchored in DOI verification and transparent protocol capture. This research received no external funding. OSF registration: Open Science Framework, 10.17605/OSF.IO/U8NHT. The manuscript reports the final included set as n = 37, states no external funding, and lists the OSF registration DOI. Full article

Visual retrievers such as visual retrieval-augmented generation (RAG) have recently emerged as a powerful model for retrieving multimodal documents without the need to convert page images into text. Existing visual retrievers typically encode every document page separately, ignoring the inherent rich context information across pages within multi-page documents. However, some crucial semantic information often spans multiple pages in a document, and should be effectively encoded for better retrieval. To address this problem, this paper proposes a novel approach utilizing dynamically fusing visual context (DFVC), which adaptively encodes the semantic information across pages. In the proposed DFVC approach, a lightweight plug-and-play adapter is designed; in addition, a contrastive loss function incorporating the positive fused embedding vectors and negative embedding vectors is designed to constrain the adapter, allowing it to learn the weights for the context pages. Together, the designed adapter and loss function allow the retriever to effectively encode useful semantic information across pages while excluding distracting noise. The proposed DFVC is validated on commonly used challenging multi-page document benchmarks. Extensive experimental results demonstrate that it significantly boosts retrieval performance. In addition, the proposed DFVC is highly parameter-efficient since it employs frozen vision-language backbones, allowing it to be easily integrated into existing visual RAG pipelines for finer document retrieval. Full article

This study challenges familiar readings of John Calvin’s theology of worship by reframing it through the lens of contemporary liturgical theology. Rather than offering a purely historical account, it probes Calvin’s intentions, achievements, and limitations, with particular attention to the formative interplay between lex orandi and lex credendi. Drawing on Calvin’s writings, liturgical texts, and patristic sources, the analysis highlights his Christological and pneumatological grounding, his integration of Word and Sacrament, his pastoral flexibility in applying the regulative principle, and his creative retrieval of ancient liturgical practices to encourage active congregational participation. At the same time, the article identifies tensions within Calvin’s approach, including the risk that doctrinal oversight may constrain liturgical vitality and contribute to an overly intellectualized understanding of worship. By juxtaposing Calvin’s historical context with contemporary ecclesial realities, the study offers both a critical reassessment and a constructive proposal: to reclaim God-centered, Scripture-shaped worship while cultivating the adaptive balance that Calvin himself sought to model. In this way, the article rearticulates the significance of Calvin’s legacy for the theological integrity and missional vitality of worship in the twenty-first century. Full article

There has been a recent increase in the use of social media platforms (SMPs), as well as a large increase in scientific journals and academic article publications. We need to study if and how much academics, scholars and researchers trust SMPs as sources, i.e., citations, for writing their research articles. The purpose of this research is to explore the relationship between SMPs and bibliographic article citations for ten years between 2010 and 2019, with 31 December marking the official identification of COVID-19, a milestone that affected the whole world, including academic publishing. By using a citation retrieval tool written in Java, the citations referring to the URLs of 6432 articles from 14 Q1 open access education journals ranked by the SCImago platform were extracted. The retrieved URLs were stored in a relational database, preprocessed and cleaned, and analyzed using SQL queries to identify and quantify citations originating from SMPs. The findings showed that there were 112 instances, which corresponds to 1.8% of the articles, of an SMP post being used as a citation. Out of the 17 SMPs checked, eight were used, with the most popular being YouTube, having a percentage of 68% of the aforementioned 112 citations, followed by Twitter (now X) with approximately 13.5% and then by Facebook with around 7%. Most of these in-text citations were found at the Introduction and the Design/Methodology sections of the papers. Other important findings of this study were that about 2% of the URL citations referred to blogs and wikis and that one in 100 articles used Wikipedia in the bibliography. Also, for a 26-year period from 1999 to 2024, it was observed that the number of journals increased by 82.8%, while the number of open access journals showed an impressive 552.14% increase. The findings of this study could lead to changes in the metadata design of bibliographic databases, like the way of searching them, and to a review of the life cycle duration of sustainable access to the content of the cited SMPs. Full article

The intestinal microbiome plays a fundamental role in canine health and well-being, regulating functions, including digestion, immunity, metabolism, and behavior. Dysbiosis refers to the disruption of the balanced composition of resident commensal communities, and gut bacteria can influence behavior via neurological, metabolic, endocrine, and immune-mediated pathways. Growing evidence supports the existence of a bidirectional communication between the gut and the central nervous system, known as the gut–brain axis, through which intestinal microorganisms may influence behavior via neurological, metabolic, endocrine, and immune-mediated pathways. Despite the expanding interest in this field, the contribution of intestinal dysbiosis to the development and severity of behavioral and neurological disorders in companion dogs remains poorly understood. This review aims to critically analyze the literature from 2011 to 18 September 2025 concerning the association between dysbiosis, the gut–brain axis, and both gastrointestinal and non-gastrointestinal illnesses in dogs. To our knowledge, this review represents the first application of Text Mining (TM) in this domain: TM facilitates the identification and analysis of valuable information from extensive datasets, converting unstructured content into structured data, thereby enabling quantitative analysis. We used the following search terms on three bibliographic databases (PubMed, Scopus, and Web of Science): “dysbiosis” AND “canine” OR “dog” AND “gut–brain axis” AND “behavior”. Of the 1176 records retrieved, 35 studies were checked following the PRISMA guidelines, and they met the predefined inclusion criteria in the final analysis. Full article

Text-based automatic compliance checking (ACC) employs natural language processing technologies to scrutinize a corporation’s business documents, ensuring adherence to related normative texts. The current methods fall into two primary categories: symbol-based and embedding-based approaches. Symbol-based methods, noted for their accuracy and transparent processing, suffer from limited versatility. Conversely, embedding-based methods operate independently of expert knowledge yet often yield challenging-to-interpret results and require substantial volumes of annotated data. While both types of methods exhibit advantages in different aspects, the current research fails to combine these advantages effectively. Therefore, the existing methods fail to balance interpretability, generalization ability, and accuracy, which are key requirements for practical compliance systems. To address this problem, we introduce a novel approach termed the Dynamic Prompt-based Logic-Aided Compliance Checker (DPLACC), which is grounded in the prompt learning framework. This method initially parses target texts, transforming the results into first-order logical expressions. It subsequently retrieves pertinent knowledge from a knowledge graph, converting the knowledge into analogous first-order logical expressions. These expressions are then encoded into a global semantic vector via a pre-trained first-order logistic encoder. Ultimately, the semantics of expressions and initial texts are amalgamated within the prompt template, facilitating the logical knowledge enhancement of model reasoning. Experiments on Chinese and English datasets demonstrate that DPLACC comprehensively outperforms existing methods based solely on symbols or embeddings in terms of accuracy, precision, recall, and F1 score and significantly surpasses current mainstream large language models. Furthermore, DPLACC exhibits enhanced interpretability and reduced data dependence, maintaining 70% checking accuracy with as few as ten training samples. This capability allows DPLACC to be rapidly deployed in data-scarce real-world scenarios with minimal annotation overhead, thus offering a practical pathway toward the scalable implementation of compliance inspection systems. Full article

Background: Automated discharge instructions are increasingly used to support post-discharge communication, patient education, and nursing follow-up, yet the current state remains unidentified. This systematic review explores the types of automated discharge instructions used and their effectiveness in enhancing patient engagement and reducing readmission, emergency department visits and reoperation rates. Methods: A systematic search was conducted on 15 April 2025, using Embase, PubMed, Scopus, Web of Science, and CINAHL, following PRISMA guidelines. Inclusion criteria required peer-reviewed original research evaluating the utilization of automated patient discharge instructions following hospital admission or surgical stay. Exclusion criteria included correspondence, reviews, educational materials, not peer-reviewed, retracted reports, not retrievable, and no English translation. Risk of bias was assessed independently using NIH, JBI, ROB-2, and ROBINS-I tools. Two investigators independently conducted the screening, extraction, and synthesis of results using Endnote and Microsoft Excel. Results: Of the 1252 records identified, 13 studies were selected for analysis. There was a total of 34,386 patients across a diverse range of healthcare settings and clinical contexts. The average sample size per study was approximately 4912, with study samples ranging from 16 to 13,188 patients. The modalities of discharge instructions included automated phone calls (23.1%) and/or text messages (53.8%), as well as printed out auto-generated summaries (15.4%). Patient engagement was generally high, with automated phone calls showing the most consistent interaction, with completion rates ranging from 44% to 56%, often prompting clinical follow-up. SMS tools demonstrated strong scalability and response rates up to 87%. Two studies reported on hospital readmission outcomes and only a single study reported on emergency department revisit rates, while none assessed reoperation outcomes. Among those reporting readmission, automated phone calls and SMS were associated with lower or proxy-reduced readmission rates. Included studies had low to moderate levels of bias. Conclusions: While evidence on clinical outcomes such as readmissions, emergency department revisits, and reoperations remains limited and inconclusive, automated discharge tools—particularly phone calls and SMS—consistently demonstrated high patient engagement. Automated discharge tools show promise for supporting transitional care, discharge education, and post-discharge monitoring, highlighting the future role of automated tools in nursing workflows to support follow-up, escalation, and continuity of care. Full article

Multimodal named entity recognition (MNER) leverages both textual and visual information to improve entity recognition, particularly in unstructured scenarios such as social media. While existing approaches predominantly rely on raster images (e.g., JPEG, PNG), scalable vector graphics (SVG) offer unique advantages in resolution independence and structured semantic representation—an underexplored potential in multimodal learning. To fill this gap, we propose MNER-SVG, the first framework that incorporates SVG as a visual modality and enhances it with ChatGPT-generated auxiliary knowledge. Specifically, we introduce a Multimodal Similar Instance Perception Module that retrieves semantically relevant examples and prompts ChatGPT to generate contextual explanations. We further construct a Full-Text Graph and a Multimodal Interaction Graph, which are processed via Graph Attention Networks (GATs) to achieve fine-grained cross-modal alignment and feature fusion. Finally, a Conditional Random Field (CRF) layer is employed for structured decoding. To support evaluation, we present SvgNER, the first MNER dataset annotated with SVG-specific visual content. Extensive experiments demonstrate that MNER-SVG achieves state-of-the-art performance with an F1 score of 82.23%, significantly outperforming both text-only and existing multimodal baselines. This work validates the feasibility and potential of integrating vector graphics and large language model-generated knowledge into multimodal NER, opening a new research direction for structured visual semantics in fine-grained multimodal understanding. 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

Geological hazard data exhibits high-volume and multi-type characteristics, specifically characterized by inherent complexity; measurement uncertainty; cross-source heterogeneity; underdeveloped semantic organization; and fragile inter-entity associations. Consequently, advanced modeling techniques coupled with robust extraction frameworks become imperative for effective unstructured data governance. To address this challenge, we propose a content–knowledge representation framework that decomposes and reconstructs disaster data using fine-grained content entities as base units. This approach allows for a unified description, objectification, ordering, hierarchical storage, and indexed categorization of unstructured information. Furthermore, we develop specialized text extraction algorithms tailored to document imagery and vector maps—facilitating the systematic application of information retrieval techniques while efficiently targeting specific thematic content. Our method outperforms two representative deep learning architectures (Fast CNN and FCN), demonstrating superior performance in segmenting target regions and precisely detecting textual elements, tables, and geographic features within complex datasets. By studying the modeling and extraction technology of unstructured geologic data, this paper establishes the value chain of geologic result data, which can provide strong support for digital management of geologic disaster data and improve work efficiency. Full article

As the prevalence of myopia, or near-sightedness, continues to rise globally, it becomes imperative to determine the mechanisms driving myopia so that appropriate interventions to mitigate it can be developed. Light appears to be critical for normal ocular development, and over the past several decades research has explored the connection between light exposure and myopia development. This review explores the growing field of photobiomodulation, or the use of light to modulate biological processes, to prevent myopia development. To complete this review, relevant texts published from January 1990 to December 2025 were retrieved from the PubMed database using a combination of search terms covering myopia and ocular development, light exposure conditions related to myopia, myopia development in relation to circadian and diurnal regulation, nonvisual opsins and myopia, and light-induced ocular damage. Through this review, we see that photobiomodulation offers a potential intervention to control myopia progression, but the mechanisms behind light’s influence on ocular development remain complex and incompletely understood. This review aims to summarize what is currently known to serve as a basis for future research and to delineate important findings. Full article

Object counting in remote sensing images is valuable for applications such as urban planning and environmental monitoring. However, it remains challenging due to heterogeneous annotations, semantic ambiguity in open-vocabulary queries, and performance degradation of small targets. To address these limitations, we propose DR-CLIP (Deformable Remote CLIP), a vision–language model for remote sensing image counting that incorporates deformable visual feature extraction with text-guided prediction. DR-CLIP includes a (1) Region-to-Instruction (R2I) mechanism to convert points, bounding boxes, and polygons into a unified image–text training representation, a (2) Multi-scale Deformable Attention (MSDA) to enhance discriminative feature extraction across extreme scale variations and cluttered backgrounds, and a (3) Text-Guided Counting Head that establishes robust cross-modal alignment through contrastive learning, achieving open-vocabulary counting capability without category-specific retraining. On DOTA-v2.0, DR-CLIP achieves a Mean Absolute Error (MAE) of 2.34 and a Root Mean Squared Error (RMSE) of 3.89, outperforming baselines by 19.0% in MAE. The MSDA module significantly increases Small-Object Recall (SOR) to 0.824, which is especially effective in situations involving dense and small object counting. In cross-modal retrieval, DR-CLIP attains R@1 scores of 68.3% (image-to-text) and 72.1% (text-to-image) on the Remote Sensing Image Captioning Dataset (RSICD). The framework generalizes robustly, with only 8.7% performance degradation in cross-domain tests, which is significantly lower than the 23.4% drop observed in baseline methods. Full article

Clinical discharge summaries contain rich patient information but remain difficult to convert into structured representations for downstream analysis. Recent advances in large language models (LLMs) have introduced new approaches for clinical text extraction, yet their relative strengths compared with supervised methods remain unclear. This study presents a controlled evaluation of three dominant strategies for structured clinical information extraction from electronic health records: prompting-based extraction using LLMs, retrieval-augmented generation for terminology canonicalization, and supervised fine-tuning of domain-specific transformer models. Using discharge summaries from the MIMIC-IV dataset, we compare zero-shot, few-shot, and verification-based prompting across closed-source and open-source LLMs, evaluate retrieval-augmented canonicalization as a post-processing mechanism, and benchmark these methods against a fine-tuned BioClinicalBERT model. Performance is assessed using a multi-level evaluation framework that combines exact matching, fuzzy lexical matching, and semantic assessment via an LLM-based judge. The results reveal clear tradeoffs across approaches: prompting achieves strong semantic correctness with minimal supervision, retrieval augmentation improves terminology consistency without expanding extraction coverage, and supervised fine-tuning yields the highest overall accuracy when labeled data are available. Across all methods, we observe a consistent $40-50\%$ gap between exact-match and semantic correctness, highlighting the limitations of string-based metrics for clinical Natural Language Processing (NLP). These findings provide practical guidance for selecting extraction strategies under varying resource constraints and emphasize the importance of evaluation methodologies that reflect clinical equivalence rather than surface-form similarity. Full article