Although multimodal Large Language Models (LLMs) perform well on document question answering tasks, Answer Correctness, i.e., whether a model’s answer is correct with respect to the question, does not fully describe model behavior because it do...
Power system testing and inspection documents are multimodal and highly structured, making content-level audit labeling challenging due to scattered evidence and cross-component dependencies. We propose EviCal, an evidence-grounded consistency calibr...
Remote sensing change captioning aims to describe disaster-related changes from bi-temporal imagery, yet existing methods typically produce image-level captions without explicit regional evidence, limiting interpretability and weakening the link betw...
Artificial intelligence systems are increasingly used for music education and music score understanding, yet most existing systems answer each task in isolation. This single-instance paradigm makes it difficult to evaluate whether an educational agen...
Historical digital personas are a promising means of interactive and personalized access to cultural heritage; however, their practical deployment requires simultaneous control over factual accuracy, source provenance, persona consistency, and multim...
Vision-based industrial safety monitoring increasingly integrates heterogeneous accidents, personal protective equipment (PPE), and semantic evidence, yet preserving their reliability, uncertainty, and provenance throughout downstream decision suppor...
Background: Mechanistic reporting from large-scale biomedical knowledge graphs remains challenging, particularly when integrating structured graph evidence with large language model (LLM)–based explanation in a reproducible and auditable manner...
Cryptographic dependency updates can install cleanly and pass visible regression tests while changing project-facing behavior or leaving an application inside a vulnerable version range. This study presents VeriCrypt-Agent, an evidence-grounded workf...
Overhead ground wires exhibit a regularly repeated stranded configuration, providing a symmetry-related perspective on their local structural organization. Local damage disrupts this regularity, introducing deviations in strand continuity, contour or...
Longitudinal electronic health records (EHRs) are a natural source of temporal QA problems, but turning them into a reliable benchmark is not simply a matter of prompting a language model to write questions and answers. We present EHRForge, a reprodu...
17 October 2023
IoT (Internet of Things)-enabled products are increasingly used by consumers and continuously propagate in daily life. Billions of networked objects not only increase the complexity of development but also raise user interaction and adaptation to ind...
Grounding systems are essential components of electrical infrastructures, ensuring personnel safety, equipment protection, and operational reliability. In the context of smart cities, these systems have evolved from passive safety elements to critica...
This study develops a multi-source site–time audit linking planning commitments, on-site delivery, and visitor use. The primary application was in Xiamen, China; the protocol was also used at five preselected sites in Songdo, South Korea. Five...
Retrieval-augmented generation and structured agent memory are commonly treated as competing ways to ground large language models. Our results show that their relative value changes with the task and that neither retrieved similarity nor graph associ...
Phishing messages have evolved from simple fraud templates into socially engineered texts that exploit anxiety, trust, relational obligation, and culturally embedded norms. In Korean phishing messages, attackers frequently combine institutional autho...
Mapping cyber-threat intelligence (CTI) to MITRE ATT&CK is usually evaluated as label prediction, yet a correct technique identifier may rest on the wrong words. We treat each mapping as an argument (a technique claim supported by textual data, a...
Artificial intelligence is increasingly deployed where direct observation, reliable ground truth, and repeatable experimentation are structurally unavailable, and pipelines resting on an externally verifiable reference fail by design. This work intro...
Background: Randomized controlled trials (rcts) provide limited evidence to support the use of survivorship care plans (scps), but they provide strong evidence for patient decision aids (ptdas). Despite that evidence, the uptake of ptdas has been lim...
The increasing complexity of online misinformation requires detection systems that supplement article-level classification with transparent, evidence-grounded, and verifiable decision support. Existing methods commonly prioritize predictive accuracy,...
Smart-classroom teaching evaluation increasingly relies on heterogeneous sensing sources, including classroom cameras, microphones, speech-recognition systems, and learning-platform interaction logs. Existing systems often treat these streams as sepa...
Long agricultural videos contain time-distributed multimodal evidence, including visual scenes, speech, subtitles, operational context, and expert explanations. Existing work remains fragmented across video perception, retrieval, summarization, monit...
28 April 2020
The COST CARES project aims to support healthcare cost containment and improve healthcare quality across Europe by developing the research and development necessary for person-centred care (PCC) and health promotion. This paper presents an overview e...
Retrieval-Augmented Generation (RAG) grounds large language models in external evidence, but many RAG systems represent knowledge either as flat text chunks or as automatically constructed indexing graphs. This assumption is incomplete for curated th...
Background/Objectives: Literature-derived knowledge graphs are attractive for drug repurposing because every edge retains its supporting publications. Their predicates, however, record which relation a sentence asserted, not whether the evidence supp...
Dataset selection is one of the most consequential methodological decisions in cybersecurity intrusion detection research. However, it is routinely made based on citation frequency, historical convention, and availability rather than principled evalu...
Large language models (LLMs) can turn a flood of cross-layer industrial logs into a fluent incident narrative, but a narrative that cites only real, resolvable events can still be wrong in every relation that matters: the login came from a different...
In recent times, deep neural networks have drawn much attention in ground-based cloud recognition. Yet such kind of approaches simply center upon learning global features from visual information, which causes incomplete representations for ground-bas...
Analyzing large-scale student feedback is critical for higher education quality assurance, yet manual analysis is inefficient and subjective. This paper proposes an integrated framework that unifies supervised classification, unsupervised clustering,...
Satellite-derived ground deformation monitoring has become an essential tool for infrastructure management; however, the spatial heterogeneity of Interferometric Synthetic Aperture Radar (InSAR) observations limits reliable assessment in regions with...
High-albedo ground and wall materials are promoted to mitigate heat stress in tropical climates, yet conflicting evidence driven by climatic and metric variability make their impact on Outdoor Thermal Comfort (OTC) unclear. This study employed parame...
Technical documents differ from general text corpora in ways that complicate retrieval-augmented generation (RAG). Evidence for a single answer is often distributed across numbered clauses, tables, figures, captions, and ordered procedures rather tha...
Smart water engineering is inherently interdisciplinary, requiring students to synthesize hydrological and hydraulic principles, observational data, domain-specific models, engineering standards, and computational tools to support evidence-based reas...
Humanities research depends on linking claims to precise evidence, such as juan, pages, passages, or time-stamped media segments. While large language models can assist with extraction and synthesis, their outputs remain difficult to use in scholarly...
Textual accounts establish essential context for port disruptions but can bias large language model synthesis before independent observations are examined. We present Port Agent, a remote-sensing agent that aligns Automatic Identification System (AIS...
Power-system safety is fundamental to protecting lives and ensuring reliable grid operation. Yet, hierarchical text classification (HTC) methods struggle with domain-dense accident narratives that require cross-sentence reasoning, often yielding limi...
Ground settlement above urban tunnels is a threat for nearby buildings, because it may lead to their differential settlement, tilting, and damage, depending on their structural characteristics, on ground conditions, and on the excavation procedure. S...
The spread of unverified health claims about drugs, dietary supplements, and alternative remedies on social media poses a growing public health concern. In this study, we present a retrieval-augmented generation (RAG) pipeline that uses large languag...
5 December 2019
With face-to-face interaction proving beneficial for mental health, there is still a paucity of research on the correlation between ground floor features (GFFs), defined here as the features of the ground floor of buildings overlooking a street, and...
Museum-grounded generative-AI guides can extend heritage interpretation from information delivery to a participatory encounter that connects what visitors understand, experience, and intend to protect. Existing research, however, rarely distinguishes...
Cross-border trade security risks are often embedded in inconsistencies among trade documents, logistics trajectories, hardware sensor states, and financial settlement activities. Existing methods primarily rely on structured declaration fields, maki...
The issue of the green development of industrial enterprises has become the focus of attention of all parties. However, the driving factors of green development behavior and performance in industrial enterprises remains unexplored. What are the drivi...
Though those who stay put in climate change hazard-prone areas are an intriguing subject of research, only a small number of empirical works specifically targeted these populations. Hence, the drivers of immobility in disaster-prone areas remain unde...
19 September 2026
Generative conversational AI can make health information easier to access, but its responses may still be unsupported, outdated, or poorly matched to the user. These risks are important in neurodevelopmental care, where occupational therapists and pa...
Pharmacogenomics (PGx) play a key role in personalized medicine by guiding drug and dosage selection based on genetics. However, the volume and complexity of PGx data hinder clinical decision-making. This research proposes a data-driven clinical deci...
Graphene and carbon nanotube (CNT) membranes are promising for filtration, desalination, and water treatment, yet their performance requires the joint interpretation of their architecture, nanoconfined transport, selectivity, fouling, swelling, defec...
Artificial high-reflectivity ground covers are a potential strategy to increase rear-side irradiance and energy yield in bifacial photovoltaic systems, especially in utility-scale plants with single-axis trackers. This paper reports field evidence fr...
Multichannel vibration from a planetary gearbox exhibits operating-condition-dependent interactions across both time scale and lag. Static undirected graphs cannot represent ordered temporal dependence, while repeated graph aggregation can attenuate...
Reservoir impoundment can reactivate pre-existing landslides and reorganize slope topography, thereby changing seepage conditions and subsequent deformation. However, crack mapping, geomorphic interpretation, and hydrodynamic diagnosis are still ofte...
The concentrations of difluoroacetic acid (DFA) and trifluoroacetic acid (TFA) in rainwater and surface water from Berlin, Germany resembled those reported for similar urban areas, and the TFA/DFA ratio in rainwater of 10:1 was in accordance with the...
Process simulation plays a crucial role in modern manufacturing, enhancing efficiency, decision making, and system optimization. However, its adoption varies across industries and regions, influenced by factors such as technological readiness, organi...
of 59