Identifying Disruptive Technologies via Dynamic Hypergraph Modeling and Large Language Models

Guideline questions are typically proposed by experts. To assess how large language models (LLMs) can support the development of guideline questions, providing insights on approaches and lessons learned. Two approaches for guideline question generation were assessed: 1) identification of questions conveyed by online search queries and 2) direct generation of guideline questions by LLMs. For the former, the researchers retrieved popular queries on allergic rhinitis using Google Trends (GT) and identified those conveying questions using both manual and LLM-based methods. They then manually structured as guideline questions the queries that conveyed relevant questions. For the second approach, they tasked an LLM with proposing guideline questions, assuming the role of either a patient or a clinician. Allergic Rhinitis and its Impact on Asthma (ARIA) 2024 guidelines. None. Frequency of relevant questions generated. The authors retrieved 3975 unique queries using GT. From these, they identified 37 questions, of which 22 had not been previously posed by guideline panel members and 2 were eventually prioritized by the panel. Direct interactions with LLMs resulted in the generation of 22 unique relevant questions (11 not previously suggested by panel members), and 4 were eventually prioritized by the panel. In total, 6 of 39 final questions prioritized for the 2024 ARIA guidelines were not initially thought of by the panel. The researchers provide a set of practical insights on the implementation of their approaches based on the lessons learned. Single case study (ARIA guidelines). Approaches using LLMs can support the development of guideline questions, complementing traditional methods and potentially augmenting questions prioritized by guideline panels. Fraunhofer Cluster of Excellence for Immune-Mediated Diseases.

Museum cultural creative products (MCCPs) represent a contemporary and tangible extension of cultural heritage, transforming intangible values and historical narratives into accessible consumer experiences. As cultural heritage institutions increasingly adopt market-oriented strategies, MCCPs have not only become a crucial medium for engaging the public with heritage through creative innovation but also a key revenue source, ensuring the sustainability and growth of these institutions. However, research on how consumers evaluate MCCPs and how these evaluations impact satisfaction remains fragmented. This study examines the relationships among product perception, consumption experience, and consumer satisfaction, integrating key indicators such as Product Creativity, Design Aesthetics, Product Functionality, Service Experience, Product Quality, Product Price, Consumer Loyalty, Emotional Response, and Cultural Perception. Using 11,035 consumer-generated reviews from e-commerce platforms, this study employs LLM-assisted semantic sentiment analysis and Partial Least Squares Structural Equation Modeling (PLS-SEM) to enhance thematic analysis and refine consumer insights, providing a more precise understanding of consumer perceptions and their effects on satisfaction. Results reveal that product perception significantly influences both consumption experience and satisfaction, with experience acting as a mediator between the two. Most notably, creativity is identified as the core dimension driving consumer satisfaction, highlighting the role of innovation in MCCP's success. Furthermore, this study extends the Diffusion of Innovation Theory by demonstrating how product creativity affects adoption and satisfaction in cultural heritage marketing. By integrating LLM-assisted semantic analysis and structural modeling, this study advances both methodological rigor and theoretical applications, offering a novel perspective on consumer perceptions in the cultural and creative industries.

Distribution network design is one of the most essential strategic decisions in logistics systems and supply chains, as it structures the network by determining the number of echelons and specifying the types, quantities, and locations of various facilities. This chapter presents decision-support models for distribution and logistics network design, covering both continuous location models (gravity location models) and discrete network design models (capacitated/uncapacitated and their relevant variants). Comprehensive numerical experiments based on the same case study offer a direct comparison of these different network design approaches. Furthermore, as one of the most disruptive technologies in Industry 5.0, the impact of generative AI (GenAI) and large language models (LLMs) on the research and education of distribution network design is thoroughly analyzed. Our experiments demonstrate that GenAI and LLMs are powerful tools in providing structured introductions to existing problems, guiding model selection and explanation, assisting with coding and code clarification, facilitating model comparison, and generating initial ideas for new research questions in distribution and logistics network design. However, they also face reliability and accuracy challenges, exhibit limited critical thinking capabilities, and struggle to address emerging research questions. Our findings offer valuable guidance for incorporating GenAI tools and LLMs into research and educational processes in distribution and logistics network design.

Large Language Models (LLMs) demonstrate potential in the field of scientific idea generation. However, the generated results often lack controllable academic context and traceable inspiration pathways. To bridge this gap, this paper proposes a scientific idea generation system called GYWI, which combines author knowledge graphs with retrieval-augmented generation (RAG) to form an external knowledge base to provide controllable context and trace of inspiration path for LLMs to generate new scientific ideas. We first propose an author-centered knowledge graph construction method and inspiration source sampling algorithms to construct external knowledge base. Then, we propose a hybrid retrieval mechanism that is composed of both RAG and GraphRAG to retrieve content with both depth and breadth knowledge. It forms a hybrid context. Thirdly, we propose a Prompt optimization strategy incorporating reinforcement learning principles to automatically guide LLMs optimizing the results based on the hybrid context. To evaluate the proposed approaches, we constructed an evaluation dataset based on arXiv (2018-2023). This paper also develops a comprehensive evaluation method including empirical automatic assessment in multiple-choice question task, LLM-based scoring, human evaluation, and semantic space visualization analysis. The generated ideas are evaluated from the following five dimensions: novelty, feasibility, clarity, relevance, and significance. We conducted experiments on different LLMs including GPT-4o, DeepSeek-V3, Qwen3-8B, and Gemini 2.5. Experimental results show that GYWI significantly outperforms mainstream LLMs in multiple metrics such as novelty, reliability, and relevance.

The incorporation of Artificial Intelligence (AI) into healthcare sector has fundamentally transformed patient care paradigms, particularly through the creation of patient education materials (PEMs) tailored to individual needs. This Study aims to assess the precision and readability AI-generated information on kidney cancer using ChatGPT 4.0, Gemini AI, and Perplexity AI., comparing these outputs to PEMs provided by the American Urological Association (AUA) and the European Association of Urology (EAU). The objective is to guide physicians in directing patients to accurate and understandable resources. PEMs published by AUA and EAU were collected and categorized. kidney cancer-related queries, identified via Google Trends (GT), were input into CahtGPT-4.0, Gemini AI, and Perplexity AI. Four independent reviewers assessed the AI outputs for accuracy grounded on five distinct categories, employing a 5-point Likert scale. A readability evaluation was conducted utilizing established formulas, including Gunning Fog Index (GFI), Simple Measure of Gobbledygook (SMOG), and Flesch-Kincaid Grade Formula (FKGL). AI chatbots were then tasked with simplifying their outputs to achieve a sixth-grade reading level. The PEM published by the AUA was the most readable with a mean readability score of 9.84 ± 1.2, in contrast to EAU (11.88 ± 1.11), ChatGPT-4.0 (11.03 ± 1.76), Perplexity AI (12.66 ± 1.83), and Gemini AI (10.83 ± 2.31). The Chatbots demonstrated the capability to simplify text lower grade levels upon request, with ChatGPT-4.0 achieving a readability grade level ranging from 5.76 to 9.19, Perplexity AI from 7.33 to 8.45, Gemini AI from 6.43 to 8.43. While official PEMS were considered accurate, the LLMs generated outputs exhibited an overall high level of accuracy with minor detail omission and some information inaccuracies. Information related to kidney cancer treatment was found to be the least accurate among the evaluated categories. Although the PEM published by AUA being the most readable, both authoritative PEMs and Large Language Models (LLMs) generated outputs exceeded the recommended readability threshold for general population. AI Chatbots can simplify their outputs when explicitly instructed. However, notwithstanding their accuracy, LLMs-generated outputs are susceptible to detail omission and inaccuracies. The variability in AI performance necessitates cautious use as an adjunctive tool in patient education.

Retrieval-augmented generation (RAG) has emerged as a significant advancement in the field of large language models (LLMs).By integrating up-to-date information not available during their initial training, RAG greatly enhances the practical utility of LLMs in realworld applications.However, even with RAG, LLMs can still produce inaccurate outputs, such as distorting or misinterpreting source content, posing risks in high-trust scenarios.To address these issues, we introduce a novel approach called Hallucination Aware Tuning (HAT).This method involves training hallucination detection models that generate detection labels and provide detailed descriptions of the detected hallucinations.Utilizing these detection results-particularly the hallucination descriptions-GPT-4 Turbo is employed to correct any detected hallucinations.The corrected outputs, free of hallucinations, along with the original versions, are used to create a preference dataset for Direct Preference Optimization (DPO) training.The fine-tuning through DPO leads to LLMs that exhibit a reduced rate of hallucinations and deliver improved answer quality.

The current study aimed to evaluate the quality, usefulness, and reliability of three large language models (LLMs)-ChatGPT-4, DeepSeek, and Gemini-in answering general questions about specific learning disorders (SLDs), specifically dyslexia and dyscalculia. For each learning disorder subtype, 15 questions were developed through expert review of social media, forums, and professional input. Responses from the LLMs were evaluated using the Global Quality Scale (GQS) and a seven-point Likert scale to assess usefulness and reliability. Statistical analyses were conducted to compare model performance, including descriptive statistics and one-way ANOVA. Results revealed no statistically significant differences in quality or usefulness across models for both disorders. However, ChatGPT-4 demonstrated superior reliability for dyscalculia (p < 0.05), outperforming Gemini and DeepSeek. For dyslexia, DeepSeek achieved 100% maximum reliability scores, while GPT-4 and Gemini scored 60%. All models provided high-quality responses, with mean GQS scores ranging from 4.20 to 4.60 for dyslexia and 3.93 to 4.53 for dyscalculia, although variability existed in their practical utility. While LLMs show promise in delivering dyslexia and dyscalculia-related information, GPT-4's reliability for dyscalculia highlights its potential as a supplementary educational tool. Further validation by professionals remains critical.

Harnessing artificial intelligence for advancements in Rice / wheat functional food Research and Development.

To achieve net-zero emissions, public policy needs to foster rapid innovation of climate technologies. However, there is a scarcity of comprehensive and up-to-date evidence to guide policymaking by monitoring climate innovation systems. This is notable, especially at the center of the innovation process, where nascent inventions transition into profitable and scalable market solutions. Here, we discuss the potential of large language models (LLMs) to monitor climate technology innovation. By analyzing large pools of unstructured text data sources, such as company reports and social media, LLMs can automate information retrieval processes and thereby improve existing monitoring in terms of cost-effectiveness, timeliness, and comprehensiveness. In this perspective, we show how LLMs can play a crucial role in informing innovation policy for the energy transition by highlighting promising use cases and prevailing challenges for research and policy.

This study examines the novel integration of Large Language Models (LLMs) into the survey development process in business and research through the development and evaluation of the Behavioral Research Assistant (BRASS) Bot. We first analyzed the traditional scale development process to identify tasks suitable for LLM integration, including both human-in-the-loop and automated LLM data collection methods. Following this analysis, we developed the details of BRASS Bot, incorporating design principles of falsifiability and reproducibility. We then conducted a comprehensive evaluation of the BRASS Bot across a diverse set of LLMs, including GPT, Claude, Gemini, and Llama, to assess its usability, validity, and reliability. We further demonstrated the practical utility of the BRASS Bot by conducting a user study and a predictive validity simulation. Our research presents both theoretical and practical implications. The augmentation approach of the BRASS Bot enriches the theoretical foundations of behavioral constructs by identifying previously overlooked patterns. Additionally, the BRASS Bot offers significant time and resource efficiency gains while enhancing scale validity. Our work lays the foundation for future research on the broader application of LLMs as both assistants and collaborators in survey analysis and behavioral research design and execution, highlighting their potential for a transformative impact on the field.

IntroductionWe developed an open, large language model (LLM)-based pipeline to extract actionable incidental findings (AIFs) from [18F]fluorodeoxyglucose positron emission tomography-computed tomography ([18F]FDG PET-CT) reports. This imaging modality often uncovers AIFs, which can affect a patient's treatment. The pipeline classifies reports for the presence of AIFs, extracts the relevant sentences, and stores the results in structured JavaScript Object Notation format, enabling use in both short- and long-term applications.MethodsTraining, validation, and test datasets of 1,999, 248, and 250 lung cancer [18F]FDG PET-CT reports, respectively, were annotated by a nuclear medicine physician. An external test dataset of 460 reports was annotated by two nuclear medicine physicians. The training dataset was used to fine-tune an LLM using QLoRA and chain-of-thought (CoT) prompting. This was evaluated quantitatively and qualitatively on both test datasets.ResultsThe pipeline achieved document-level F1 scores of 0.917 ± 0.016 and 0.79 ± 0.025 on the internal and external test datasets. At the sentence-level, F1 scores of 0.754 ± 0.011 and 0.522 ± 0.012 were recorded, and qualitative analysis demonstrated even higher practical utility. This qualitative analysis revealed how sentence-level performance is better in practice.DiscussionLlama-3.1-8B Instruct was the base LLM that provided the best combination of performance and computational efficiency. The utilisation of CoT prompting improved performance further. Radiology reporting characteristics such as length and style affect model generalisation.ConclusionWe find that a QLoRA-adapted LLM utilising CoT prompting successfully extracts AIF information at both document- and sentence-level from both internal and external PET-CT reports. We believe this model can assist with short-term clinical challenges like clinical alerts and reminders, and long-term tasks like investigating comorbidities.

Large language models (LLMs) have demonstrated logical reasoning abilities, but their inferences remain non-traceable and lack formal guarantees. We introduce eXa-LM, a controlled natural language (CNL) interface between LLMs and first-order logic solvers. Based on a Controlled Natural Language, our approach aims to create an explicit, verifiable, and interpretable bridge between text and formal logic. It relies on three main components: (1) a reformulation prompt that constrains the LLM to produce a set of facts and rules in CNL, (2) the semantic analyzer eXaSem translating this CNL into a Prolog program made of extended Horn clauses, and (3) the logic engine eXaLog, which integrates a second-order meta-interpreter capable of inferring ontological properties.We evaluate eXa-LM on three standard benchmarks—PrOntoQA, ProofWriter and FOLIO—comparing it to GPT-4o baselines including Standard prompting, Chain-of-Thought, Logic-LM, LINC, and LLM-TP. Results show that eXa-LM matches or exceeds recent neuro-symbolic systems while providing full traceability of reasoning and intrinsic explainability. On FOLIO, eXa-LM achieves 92.9% accuracy, a +5.5 point gain over LLM-TP, the strongest competing GPT-4o-based method in our comparison.This approach demonstrates the feasibility of a transparent neuro-symbolic reasoning pipeline in which LLMs produce not direct inferences but formally controlled linguistic representations. eXa-LM opens the way to neuro-symbolic architectures that are safer, verifiable and extensible, ultimately integrating hypothetical, abductive or inductive reasoning. Program and data will be made publicly available upon publication.

The rapid retrieval and precise acquisition of land use approval information are crucial for enhancing the efficiency and quality of land use approval, as well as for promoting the intelligent transformation of land use approval processes. As an advanced retrieval method, question-answering (Q&amp;A) technology has become a core technical support for addressing current issues such as low approval efficiency and difficulty in obtaining information. However, existing Q&amp;A technologies suffer from significant hallucination problems and limitations in considering spatiotemporal factors in the land use approval domain. To effectively address these issues, this study proposes a spatiotemporal–semantic coupling intelligent Q&amp;A method for land use approval based on knowledge graphs (KGs) and intelligent agent technology, aiming to enhance the efficiency and quality of land use approval. Firstly, a land use approval knowledge graph (LUAKG) is constructed, systematically integrating domain knowledge such as policy clauses, legal regulations, and approval procedures. Then, by combining large language models (LLMs) and intelligent agent technology, a spatiotemporal–semantic coupling Q&amp;A framework is designed. Through the use of spatiotemporal analysis tools, this framework can comprehensively consider spatial, temporal, and semantic factors when handling land approval tasks, enabling dynamic decision-making and precise reasoning. The research results show that, compared to traditional Q&amp;A based on LLMs and Q&amp;A based on retrieval-enhanced generation (RAG), the proposed method improves accuracy by 16% and 9% in general knowledge Q&amp;A tasks. In the project review Q&amp;A task, F1 scores and accuracy increase by 2% and 9%, respectively, compared to RAG-QA. Particularly, under the spatiotemporal–semantic multidimensional analysis, the improvement in F1 score and accuracy ranges from 2 to 6% and 7 to 10%, respectively.

Large language models like ChatGPT can enhance patients' understanding of medical information, making health decisions more accessible. Complex terms, such as "fragility fracture," can confuse patients, so presenting its medical content in plain language is crucial. This study explored whether conversational prompts improve readability and understanding compared to keyword-based prompts when generating patient-centered health information on fragility fractures. The 32 most frequently searched keywords related to "fragility fracture" and "osteoporotic fracture" were identified using Google Trends. From this set, 24 keywords were selected based on relevance and entered sequentially into ChatGPT. Each keyword was tested with two prompt types: (1) plain language with keywords embedded and (2) keywords alone. The readability and comprehensibility of the AI-generated responses were assessed using the Flesch-Kincaid reading ease (FKRE) and Flesch-Kincaid grade level (FKGL), respectively. The scores of the responses were compared using the Mann-Whitney U test. The FKRE scores indicated significantly higher readability with plain language prompts (median 34.35) compared to keyword-only prompts (median 23.60). Similarly, the FKGL indicated a lower grade level for plain language prompts (median 12.05) versus keyword-only (median 14.50), with both differences achieving statistical significance. Our findings suggest that using conversational prompts can enhance the readability of AI-generated medical information on fragility fractures. Clinicians and content creators should consider this approach when using AI for patient education to optimize comprehension.

Comparative evaluation of large language models for patient education after total knee arthroplasty.