ARTIFICIAL INTELLIGENCE REVIEW人工智能评论
ARTIFICIAL INTELLIGENCE REVIEW(英文缩写 ARTIF INTELL REV),ISSN 0269-2821,eISSN 1573-7462,中文译名:人工智能评论 是一本学术期刊。本页汇总该期刊的最新影响因子、分区信息以及最新收录于 PubMed 的文献,帮助您快速了解期刊全貌。
发文量统计区间：2025-11-01 至 2026-10-31，按本站收录文献的发表日期统计。
期刊介绍
历年影响因子趋势
| JCR 数据年份 | 影响因子 | JCR 分区 |
|---|---|---|
| 2021 | 9.588 | Q1 |
| 2022 | 12.000 | Q1 |
| 2023 | 10.700 | Q1 |
| 2024 | 13.900 | Q1 |
| 2025 | 18.800 | Q1 |
ARTIFICIAL INTELLIGENCE REVIEW 最新收录文献
-
1. An auditable pipeline for fuzzy full-text screening in systematic reviews: integrating contrastive semantic highlighting and LLM judgment.
PMID:日期:2026-05-26Full-text screening is the major bottleneck of systematic reviews (SRs), particularly in domains such as population health modelling of noncommunicable diseases (NCDs), where decisive eligibility information is scattered across long and heterogeneous full texts. In this methodological study, we introduce a scalable and auditable pipeline that reframes inclusion and exclusion as a fuzzy decision process. We evaluate the approach within the Population Health Modelling Consensus Reporting Network (POPCORN) and benchmark it against statistical and crisp baselines. Articles are parsed into overlapping chunks and embedded with a domain-adapted model; for each criterion (Population, Intervention, Outcome, Study Approach), we compute contrastive similarity (inclusion-exclusion cosine) and a , which a Mamdani fuzzy controller maps into graded inclusion degrees with dynamic thresholds in a multi-label classification setting. A large language model (LLM) judge adjudicates highlighted spans with tertiary labels, confidence scores, and criterion-referenced rationales; when evidence is insufficient, fuzzy membership is attenuated rather than hard-excluded. In a pilot on an all-positive gold set ([Formula: see text] full texts; [Formula: see text] chunks), the fuzzy system achieved document-level recall of 81.25% (Population), 87.50% (Intervention), 87.50% (Outcome), and 75.00% (Study Approach) with 95% Wilson confidence intervals, exceeding statistical baselines (recall 56.25-75.00%) and crisp baselines (recall 43.75-81.25%). Strict "All Criteria" inclusion was reached for 50.00% of articles, compared to 25.00% and 12.50% under the baselines. Cross-model agreement on justifications was 98.27%, and human-machine agreement was 96.07%. A pilot review showed 91% inter-rater agreement ([Formula: see text]) with screening time reduced from 20 minutes to under 1 minute per article at a significantly lower cost. These results suggest that fuzzy logic, combined with contrastive highlighting and explainable LLM adjudication, delivers high recall, stable rationales, and end-to-end traceability. We emphasize that the reported recall figures were computed on an all-positive gold set (no excluded documents), so specificity, ROC/PR curves, and AUC are not defined here; the complete operating-characteristic analysis on a mixed-label corpus will be reported in a forthcoming study.
-
2. Quantum adversarial machine learning: from classical adaptations to quantum-native methods.
PMID:日期:2026-05-11Machine learning has revolutionized numerous industrial domains. Despite recent advances, machine learning models remain vulnerable to adversarial threats. Adversarial machine learning is a field that studies these vulnerabilities to build robust machine learning models. Quantum machine learning is an interdisciplinary field that bridges quantum computing and classical machine learning. While quantum machine learning shows potentials to outperform classical machine learning in complex tasks such as regression, classification, and generative modeling, it remains vulnerable to adversarial attacks. Given the recent advancements in quantum computing and machine learning, the quantum adversarial machine learning field has emerged to study the vulnerabilities of quantum machine learning, possible attacks, and novel quantum-enhanced defense strategies. In this survey, we provide a detailed overview on quantum adversarial machine learning and explore the existing attacks and countermeasures. We also review the theoretical underpinnings of this area, emerging trends, and critical challenges.
-
3. Super greedy trees.
PMID:日期:2026-03-22We introduce Super Greedy Trees (SGTs), a decision-tree framework that extends CART by constructing tree splits from lasso-penalized parametric models. At each tree node, a model fitted to the local data induces an adaptive multivariate geometric cut (linear or curved) selected to greedily reduce empirical risk. This yields richer partitions than axis-parallel CART while keeping each split easy to inspect through sparse local structure. In simulated and real-world regression studies, SGTs and an ensemble extension (Super Greedy Forests, SGFs) perform well relative to CART, oblique trees, random forests, and gradient boosted trees, especially when the underlying response surface is complex. In a treadmill ECG and clinical-data case study, SGFs identify sparse combinations of signals associated with long-term survival. The SGT framework thus provides a flexible and theoretically sound approach to tree-based learning.
-
4. Artificial neural networks fighting real neural decline: a systematic review of AI in Alzheimer's research.
PMID:日期:2026-02-02Alzheimer's disease (AD) is a major global health challenge, with Artificial Intelligence (AI) increasingly recognized as a transformative tool for early detection, disease progression modeling, and therapeutic discovery. This systematic review, conducted in accordance with PRISMA guidelines, analyzed 156 peer-reviewed studies published between 2010 and 2024, identified from four major databases (Scopus, PubMed, Web of Science, IEEE Xplore). A particular emphasis was placed on multimodal approaches that integrate neuroimaging, genetics, biomarkers, and clinical data to improve accuracy and translational value. To organize this fragmented field, we introduce a novel Layered Framework that categorizes AI applications into four domains: Early Detection, Disease Progression Modeling, Therapeutic Discovery, and Real-World Integration. In addition, we applied ARIMA-based forecasting to project research trajectories through 2030, which revealed generative models and transformer architectures as the fastest-growing and most promising methodologies. The review highlights substantial advances in early detection and multimodal fusion, particularly through deep learning, while also identifying persistent challenges such as limited model generalizability, ethical concerns, and underexplored clinical implementation. Addressing these barriers will require multi-cohort validation, interpretable AI, and equity-driven model development. By consolidating evidence and forecasting future directions, this review provides a roadmap for accelerating precision-driven innovations in Alzheimer's care.
-
5. Advances in artificial intelligence: a review for the creative industries.
PMID:日期:2026-01-24Artificial intelligence (AI) has undergone transformative advances since 2022, particularly through generative AI, large language models (LLMs), and diffusion models, fundamentally reshaping the creative industries. However, existing reviews have not comprehensively addressed these recent breakthroughs and their integrated impact across the creative production pipeline. This paper addresses this gap by providing a systematic review of AI technologies that have emerged or matured since our 2022 review, examining their applications across content creation, information analysis, post-production enhancement, compression, and quality assessment. We document how transformers, LLMs, diffusion models, and implicit neural representations have established new capabilities in text-to-image/video generation, real-time 3D reconstruction, and unified multi-task frameworks-shifting AI from support tool to core creative technology. Beyond technological advances, we analyze the trend toward unified AI frameworks that integrate multiple creative tasks, replacing task-specific solutions. We critically examine the evolving role of human-AI collaboration, where human oversight remains essential for creative direction and mitigating AI hallucinations. Finally, we identify emerging challenges including copyright concerns, bias mitigation, computational demands, and the need for robust regulatory frameworks. This review provides researchers and practitioners with a comprehensive understanding of current AI capabilities, limitations, and future trajectories in creative applications.
-
6. Topological data analysis and topological deep learning beyond persistent homology: a review.
PMID:日期:2025-12-21Topological data analysis (TDA) is a rapidly evolving field in applied mathematics and data science that leverages tools from topology to uncover robust, shape-driven, and explainable insights in complex datasets. The main workhorse is persistent homology, a technique rooted in algebraic topology. Paired with topological deep learning (TDL) or topological machine learning, persistent homology has achieved tremendous success in a wide variety of applications in science, engineering, medicine, and industry. However, persistent homology has many limitations due to its high-level abstraction, insensitivity to non-topological changes, and restriction to point cloud data. This paper presents a comprehensive review of TDA and TDL beyond persistent homology. It analyzes how persistent topological Laplacians and Dirac operators provide spectral representations to capture both topological invariants and homotopic evolution. Other formulations are presented in terms of sheaf theory, Mayer topology, and interaction topology. For data on differentiable manifolds, techniques rooted in differential topology, such as persistent de Rham cohomology, persistent Hodge Laplacian, and Hodge decomposition, are reviewed. For one-dimensional (1D) curves embedded in 3-space, approaches from geometric topology are discussed, including multiscale Gauss-link integrals, persistent Jones polynomials, and persistent Khovanov homology. This paper further discusses the appropriate selection of topological tools for different input data, such as point clouds, sequential data, data on manifolds, curves embedded in 3-space, and data with additional non-geometric information. A review is also given of various topological representations, software packages, and machine learning vectorizations. Finally, this review ends with concluding remarks.
-
7. Exploring unanswerability in machine reading comprehension: approaches, benchmarks, and open challenges.
PMID:日期:2025-11-25The challenge of unanswerable questions in Machine Reading Comprehension (MRC) has drawn considerable attention, as current MRC systems are typically designed under the assumption that every question has a valid answer within the provided context. However, these systems often encounter real-world situations where no valid answer is available. This paper provides a comprehensive review of existing methods for addressing unanswerable questions in MRC systems, categorizing them into model-agnostic and model-specific approaches. It explores key strategies, examines relevant datasets, and evaluates commonly used metrics. This work aims to provide a comprehensive understanding of current techniques and identify critical gaps in the field, offering insights and key challenges to direct future research toward developing more robust MRC systems capable of handling unanswerable questions.
-
8. Knowledge distillation and dataset distillation of large language models: emerging trends, challenges, and future directions.
PMID:日期:2025-11-20The exponential growth of Large Language Models (LLMs) continues to highlight the need for efficient strategies to meet ever-expanding computational and data demands. This survey provides a comprehensive analysis of two complementary paradigms: Knowledge Distillation (KD) and Dataset Distillation (DD), both aimed at compressing LLMs while preserving their advanced reasoning capabilities and linguistic diversity. We first examine key methodologies in KD, such as task-specific alignment, rationale-based training, and multi-teacher frameworks, alongside DD techniques that synthesize compact, high-impact datasets through optimization-based gradient matching, latent space regularization, and generative synthesis. Building on these foundations, we explore how integrating KD and DD can produce more effective and scalable compression strategies. Together, these approaches address persistent challenges in model scalability, architectural heterogeneity, and the preservation of emergent LLM abilities. We further highlight applications across domains such as healthcare and education, where distillation enables efficient deployment without sacrificing performance. Despite substantial progress, open challenges remain in preserving emergent reasoning and linguistic diversity, enabling efficient adaptation to continually evolving teacher models and datasets, and establishing comprehensive evaluation protocols. By synthesizing methodological innovations, theoretical foundations, and practical insights, our survey charts a path toward sustainable, resource-efficient LLMs through the tighter integration of KD and DD principles.
-
9. Validation is the central challenge for generative social simulation: a critical review of LLMs in agent-based modeling.
PMID:日期:2025-11-18Recent advances in Large Language Models (LLMs) have revitalized interest in Agent-Based Models (ABMs) by enabling "generative" simulations, with agents that can plan, reason, and interact through natural language. These developments promise greater realism and expressive power, but also revive long-standing concerns over empirical grounding, calibration, and validation-issues that have historically limited the uptake of ABMs in the social sciences. This paper systematically reviews the emerging literature on generative ABMs to assess how these long-standing challenges are being addressed. We map domains of application, categorize reported validation practices, and assess their alignment with the stated modeling goals. Our review suggests that the use of LLMs may exacerbate rather than alleviate the challenge of validating ABMs, given their black-box structure, cultural biases, and stochastic outputs. While the need for validation is increasingly acknowledged, studies often rely on face-validity or outcome measures that are only loosely tied to underlying mechanisms. Generative ABMs thus occupy an ambiguous methodological space-lacking both the parsimony of formal models and the empirical validity of data-driven approaches-and their contribution to cumulative social-scientific knowledge hinges on resolving this tension.
-
10. Individual variable priority: a model-independent local gradient method for variable importance.
PMID:日期:2025-11-05Traditional variable importance measures quantify overall feature contributions but often overlook individual-level heterogeneity. Several new procedures attempt to address this limitation but remain model dependent and may introduce biases. We propose individual variable priority (iVarPro), an extension of the Variable Priority (VarPro) framework, which uses rule-based, data-driven partitioning to estimate the gradient of the conditional mean function. By focusing on gradients, iVarPro captures how small perturbations in a variable influence an individual's outcome, providing a more precise and interpretable measure of importance. To demonstrate its advantages, we conducted simulations and analyzed a real-world survival dataset. Our results show that iVarPro more accurately captures the true functional relationship by flexibly leveraging local samples.