Search Results (477)

Objectives: The increasing incidence of unruptured intracranial aneurysms (UIAs) has led to significant demands on neurovascular boards. Large language models (LLMs), such as ChatGPT-4, ChatGPT-3.5, Claude, and Atlas GPT, have emerged as tools to support clinical decision-making. This study compares treatment recommendations from these AI models with those of an interdisciplinary neurovascular board to evaluate their accuracy and alignment. Methods: We retrospectively included all 57 patients with UIAs discussed by the neurovascular board in 2023. The board’s consensus decision served as the reference standard. Key clinical and radiographic data, including PHASES, ELAPSS, and UIATS scores, were provided to the AI models. Each model was tasked with recommending either conservative or operative management and specifying the treatment modality (clipping, coiling, flow diverter, or WEB device/flow diverter) where appropriate. AI model recommendations were compared with the board’s decisions for management and the specific treatment modality of the UIA. Results: ChatGPT-4 achieved the highest accuracy in correctly predicting conservative or operative management (89%) and specific treatment types (73%), followed by Atlas GPT (74% accuracy in conservative/operative decisions and 55% accuracy in specific treatment types), Claude (70% accuracy in conservative/operative decisions and 50% accuracy in specific treatment types), and ChatGPT-3.5 (82% accuracy in conservative/operative decisions and 27% accuracy in specific treatment types). ChatGPT-3.5 displayed a strong preference for clipping (94.3%). ELAPSS scores significantly influenced AI recommendations and decision-making, particularly for ChatGPT-4 and ChatGPT-3.5. Follow-up recommendations for conservative management were shorter among AI models, with Claude suggesting the shortest interval (7.72 months) compared to the neurovascular board’s 13.36 months. Conclusions: AI models, particularly ChatGPT-4, align closely with expert neurovascular board decisions and offer promising support for initial clinical decision-making, particularly in resource-limited settings. However, interdisciplinary neurovascular boards remain unreplaceable for UIA management, and AI should be viewed as a complementary tool. The observed improvement from ChatGPT-3.5 to ChatGPT-4 underscores the rapid evolution of AI technology, and further advancements are expected to enhance both performance and accuracy in the future. Full article

The rapid development of deep learning (DL) has demonstrated its modular contributions to artificial intelligence (AI) techniques, such as large language models (LLMs). DL variants have proliferated across domains such as feature extraction, normalization, lightweight architecture design, and module integration, yielding substantial advancements in these subfields. However, the absence of a unified review framework to contextualize DL’s modular evolutions within AI development complicates efforts to pinpoint future research directions. Existing review papers often focus on narrow technical aspects or lack systemic analysis of modular relationships, leaving gaps in our understanding how these innovations collectively drive AI progress. This work bridges this gap by providing a roadmap for researchers to navigate DL’s modular innovations, with a focus on balancing scalability and sustainability amid evolving AI paradigms. To address this, we systematically analyze extensive literature from databases including Web of Science, Scopus, arXiv, ACM Digital Library, IEEE Xplore, SpringerLink, Elsevier, etc., with the aim of (1) summarizing and updating recent developments in DL algorithms, with performance benchmarks on standard dataset; (2) identifying innovation trends in DL from a modular viewpoint; and (3) evaluating how these modular innovations contribute to broader advances in artificial intelligence, with particular attention to scalability and sustainability amid shifting AI paradigms. Full article

The current agent-based evolutionary models for animal communication rely on simplified signal representations that differ significantly from natural vocalizations. We propose a novel agent-based evolutionary model based on text-to-audio (TTA) models to generate realistic animal vocalizations, advancing from VAE-based real-valued genotypes to TTA-based textual genotypes that generate bird songs using a fine-tuned Stable Audio Open 1.0 model. In our sexual selection framework, males vocalize songs encoded by their genotypes while females probabilistically select mates based on the similarity between males’ songs and their preference patterns, with mutations and crossovers applied to textual genotypes using a large language model (Gemma-3). As a proof of concept, we compared TTA-based and VAE-based sexual selection models for the Blue-and-white Flycatcher (Cyanoptila cyanomelana)’s songs and preferences. While the VAE-based model produces population clustering but constrains the evolution to a narrow region near the latent space’s origin where reconstructed songs remain clear, the TTA-based model enhances the genotypic and phenotypic diversity, drives song diversification, and fosters the creation of novel bird songs. Generated songs were validated by a virtual expert using the BirdNET classifier, confirming their acoustic realism through classification into related taxa. These findings highlight the potential of combining large language models and TTA models in agent-based evolutionary models for animal communication. 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

Social media provides a vital arena for rare disease (RD) communities, fostering support, advocacy, and knowledge sharing. Rare Disease Day generates a large-scale online conversation, yet previous research has relied mainly on static, cross-sectional snapshots. This study captures the longitudinal evolution of the Spanish-language Twitter debate around Rare Disease Day across a fixed yearly window (1 February to 15 March) from 2008 to 2023. After filtering for Spanish-language posts, a corpus of 308,823 tweets (72,740 originals) was analyzed. We combined hashtag frequency analysis to assess topic salience with social network analysis (SNA) of co-occurrence networks to identify central thematic clusters. Results show progression from early generic expressions to increasingly deliberate, action-oriented communication, reflecting a shift towards empowered activism. A headline finding is the structural centrality and persistence of the hashtag #investigación (#research), underscoring the community’s enduring call for scientific progress. SNA further revealed the difference between transient virality—often linked to political or celebrity-driven hashtags—and the stable, identity-related topics at the core of the debate. Longitudinal hashtag analysis, particularly using SNA, provides a powerful tool to identify stable priorities of online health communities beyond transient media noise. Full article

Despite growing global concern, the gender pay gap (GPG) within China’s financial sector remains underexplored through systematic, data-driven approaches. This study presents one of the few, if not the only, systematic literature review (SLR) and bibliometric analyses focused on the GPG in this context, aiming to map the intellectual landscape, thematic evolution, and policy relevance of the field. Peer-reviewed English-language articles published between 1975 and 2025 were retrieved from the Web of Science Core Collection, enabling international benchmarking and citation mapping. A three-tiered screening protocol narrowed 209 initial records to 64 eligible studies. Bibliometric tools, including VOSviewer and R Bibliometrix, were applied to visualize co-authorship and co-citation networks. The analysis revealed three dominant research clusters—salary transparency, organizational barriers, and leadership gaps—while identifying emerging intersections with FinTech, ESG, and intersectionality frameworks. Despite these trends, the findings indicate limited citation influence, thematic fragmentation, and weak scholarly integration. While the exclusion of Chinese-language literature is a limitation, it is justified for comparative consistency. Overall, this study demonstrates how combining bibliometrics with policy analysis uncovers underexplored “invisible metrics” that sustain gender disparities. It provides a foundational evidence base for future academic inquiry and actionable reforms aligned with SDG 5 and ESG mandates. Full article

The internet’s evolution as a global communication nexus has enabled unprecedented connectivity, allowing users to share information, media, and personal updates across social platforms. However, these platforms also amplify risks such as cyberbullying, cyberstalking, and other forms of online abuse. Cyberbullying, in particular, causes significant psychological harm, disproportionately affecting young users and females. This work leverages recent advances in Natural Language Processing (NLP) to design a robust and privacy-preserving framework for detecting abusive language on social media. The proposed approach integrates ensemble federated learning (EFL) and transfer learning (TL), combined with differential privacy (DP), to safeguard user data by enabling decentralized training without direct exposure of raw content. To enhance transparency, Explainable AI (XAI) methods, such as Local Interpretable Model-agnostic Explanations (LIME), are employed to clarify model decisions and build stakeholder trust. Experiments on a balanced benchmark dataset demonstrate strong performance, achieving 98.19% baseline accuracy and 96.37% with FL and DP respectively. While these results confirm the promise of the framework, we acknowledge that performance may differ under naturally imbalanced, noisy, and large-scale real-world settings. Overall, this study introduces a comprehensive framework that balances accuracy, privacy, and interpretability, offering a step toward safer and more accountable social networks. Full article

This article critically examines the evolution of EU migration policy discourse from 1989 to 2024, highlighting the shift from overt securitization to a more humanitarian and managerial framing, which still retains some securitization elements. By analyzing key policy documents, including the Hague and Stockholm Programmes, the Global Approach to Migration and Mobility (GAMM), and the 2024 Pact on Migration and Asylum, this paper demonstrates how migration has been increasingly framed as a technical and economic issue while still maintaining exclusionary logics. Although humanitarian language has softened, policy goals remain focused on containment, selective inclusion, and externalizing responsibility. The second part of the article explores the religious aspect of EU migration policy, arguing that, despite the formal secularism of EU institutions, religious identity, particularly Islam, is implicitly intertwined with discourses of risk, cultural incompatibility, and integration. Drawing on Peter Berger’s theory of pluralism, the paper highlights a fundamental tension between the EU’s normative claims to diversity and its implicit preference for secular Christian frameworks. The analysis examines pathways for integrating religious consultation into EU governance and its potential to address the persistent marginalization of religion as a factor in inclusion and political agency. By linking migration discourse to the often-overlooked role of religion, this article calls for a more coherent, pluralist-informed EU strategy for migration and integration. Full article

Chemical synaptic coupling is crucial in the nervous system. This paper establishes a chemical synaptic Chay neuronal coupling system using the Heaviside function and analyzes the equilibrium point’s type and stability based on the Jacobian matrix. Matcont simulation found that the Hopf bifurcation point transformed into a Bogdanov–Takens bifurcation point under the influence of chemical coupling strength, and a series of saddle-node bifurcation points are generated. The discharge time history of the system and the evolution of single-parameter bifurcation behavior were numerically simulated through a language and Matlab. The parameter matching results indicated that the chemical synaptic reversible potentials and synaptic thresholds were −15 mV and −35 mV, respectively. The bifurcation behavior and its changes under multi-parameter conditions were studied by using various numerical methods such as time series diagrams, bifurcation diagrams, and two-parameter diagrams. The similarity function identified key factors affecting synchrony in a chemical synaptic coupling system. Results indicate that synchrony primarily depends on chemical coupling strength, with other factors providing positive feedback to enhance it. The simulation of the spatiotemporal dynamics in a chemically synaptic coupled network of 2000 ring neurons revealed that altering the maximum conductance at local positions within the network can induce the generation of traveling waves. Strong coupling strengths ensure that the induced traveling waves propagate at greater velocities and can excite and awaken a larger number of neurons in a shorter time frame. The nonlinear properties of chemical synaptic neuronal system offer essential tools and foundations for studying neurobiology and brain dynamics. Full article

In today’s fast-paced release cycles, mobile app user reviews offer a valuable source for tracking the evolution of user needs. At the core of these needs lies a structure of interdependencies—some enhancements are only relevant in specific usage contexts, while others may conflict when implemented together. Identifying these relationships is essential for anticipating feature interactions, resolving contradictions, and enabling context-aware, user-driven planning. The present work introduces an ontology-enhanced AI framework for predicting whether the requirements mentioned in reviews are interdependent. The core component is a Bidirectional Encoder Representations from Transformers (BERT) classifier retrained within a large-language-model-driven active learning loop that focuses on instances with uncertainty. The framework integrates contextual and structural reasoning; contextual analysis captures the semantic intent and functional role of each requirement, enriching the understanding of user expectations. Structural reasoning relies on a domain-specific ontology that serves as both a knowledge base and an inference layer, guiding the grouping of requirements. The model achieved strong performance on annotated banking app reviews, with a validation F1-score of 0.9565 and an area under the ROC curve (AUC) exceeding 0.97. The study results contribute to supporting developers in prioritizing features based on dependencies and delivering more coherent, conflict-free releases. Full article

This survey provides an in-depth review of large language models (LLMs), highlighting the significant paradigm shift they represent in artificial intelligence. Our purpose is to consolidate state-of-the-art advances in LLM design, training, adaptation, evaluation, and application for both researchers and practitioners. To accomplish this, we trace the evolution of language models and describe core approaches, including parameter-efficient fine-tuning (PEFT). The methodology involves a thorough survey of real-world LLM applications across the scientific, engineering, healthcare, and creative sectors, coupled with a review of current benchmarks. Our findings indicate that high training and inference costs are shaping market structures, raising economic and labor concerns, while also underscoring a persistent need for human oversight in assessment. Key trends include the development of unified multimodal architectures capable of processing varied data inputs and the emergence of agentic systems that exhibit complex behaviors such as tool use and planning. We identify critical open problems, such as detectability, data contamination, generalization, and benchmark diversity. Ultimately, we conclude that overcoming these complex technical, economic, and social challenges necessitates collaborative advancements in adaptation, evaluation, infrastructure, and governance. Full article

The urban heat island (UHI) effect, intensified by urbanisation and climate change, leads to increased urban temperatures and poses a serious environmental challenge. Understanding its causes, impacts, and mitigation strategies is essential for sustainable urban planning. The aim of this study is to systematically analyse how the Urban Heat Island (UHI) effect has been addressed in the scientific literature, to identify key research themes and their temporal evolution, and to critically highlight knowledge gaps in order to provide guidance for future research and urban planning policies. Using BERTopic, an advanced natural language processing (NLP) tool, the study extracts dominant themes from a large corpus of academic literature and tracks their evolution over time. A total of 9061 research articles from the Web of Science database were collected, pre-processed, and analysed. BERTopic clustered semantically related topics and revealed their temporal dynamics, offering insights into emerging and declining research areas. The results show that pavement materials and urban vegetation are among the most studied themes, highlighting the importance of surface materials and green infrastructure in mitigating UHI. In line with this aim, the study identifies a rising interest in urban cooling strategies, particularly reflective surfaces and ventilation corridors. Consistent with its aim, the study provides a comprehensive overview of UHI literature, critically identifies existing gaps, and proposes clear directions for future research. It provides supports for urban planners, policymakers, and researchers in developing data-driven strategies to mitigate UHI impacts and strengthen enhance urban climate resilience. Full article

Large language models (LLMs) have become essential in various use cases, such as code generation, reasoning, or translation. Applications vary from language understanding to decision making. Despite this rapid evolution, significant concerns appear regarding the security of these models and the vulnerabilities they present. In this research, we present an overview of the common LLM models, and their design components and architectures. Moreover, we present their domains of applications. Following that, we present the main security concerns associated with LLMs as defined in different security referentials and standards such as OWASP, MITRE, and NIST. Moreover, we present prior research that focuses on the security concerns in LLMs. Finally, we conduct a comparative study of the performance and robustness of several models against various attack scenarios. We highlight the behavior differences of these models, which prove the importance of giving more attention for the security aspect when using or designing LLMs. Full article

Corporate sustainability reporting is increasingly scrutinised as stakeholders’ demand credible commitments to environmental and social performance, especially in sectors where unsustainable practices are pervasive. The aim of this research is to examine—drawing on a systematic literature review (SLR) of 48 articles—how leadership discourse in sustainability reports influences stakeholder engagement and reflects the adoption of sustainable development standards over time. A longitudinal analysis of six years (2018–2023) of sustainability reports from a leading fast fashion company was conducted, integrating Topic Modelling to identify dominant themes in leadership communication and comparing them with key performance indicators related to climate, materials, energy, water, waste, and packaging. The results reveal a gradual evolution in leadership narratives, from broad aspirational statements emphasising ethical supply chains and social justice to more technical, performance-oriented language highlighting circularity, operational transparency, and climate action. However, the analysis also uncovers inconsistencies between declared objectives and measurable outcomes, suggesting tensions between symbolic and substantive sustainability commitments. These findings indicate that, while leadership discourse can mobilise stakeholder expectations and signal strategic priorities, its credibility depends on alignment with transparent, consistent performance data. This study contributes to understanding how discourse and practice interact in sustainability transitions, offering insights for enhancing reporting integrity. Full article

This entry presents a comprehensive overview of the computational study of Old English that surveys the evolution from early digital corpora to recent artificial intelligence applications. Six interconnected domains are examined: textual resources (including the Helsinki Corpus, the Dictionary of Old English Corpus, and the York-Toronto-Helsinki Parsed Corpus), lexicographical resources (analysing approaches from Bosworth–Toller to the Dictionary of Old English), corpus lemmatisation (covering both prose and poetic texts), treebanks (particularly Universal Dependencies frameworks), and artificial intelligence applications. The paper shows that computational methodologies have transformed Old English studies because they facilitate large-scale analyses of morphology, syntax, and semantics previously impossible through traditional philological methods. Recent innovations are highlighted, including the development of lexical databases like Nerthusv5, dependency parsing methods, and the application of transformer models and NLP libraries to historical language processing. In spite of these remarkable advances, problems persist, including limited corpus size, orthographic inconsistency, and methodological difficulties in applying modern computational techniques to historical languages. The conclusion is reached that the future of computational Old English studies lies in the integration of AI capabilities with traditional philological expertise, an approach that enhances traditional scholarship and opens new avenues for understanding Anglo-Saxon language and culture. Full article