Lecture notes in computer science, Год журнала: 2025, Номер unknown, С. 107 - 119
Опубликована: Янв. 1, 2025
Язык: Английский
Critical Reviews in Food Science and Nutrition, Год журнала: 2024, Номер unknown, С. 1 - 16
Опубликована: Фев. 13, 2024
Machine learning (ML) technology is a powerful tool in food science and engineering offering numerous advantages, from recognizing patterns predicting outcomes to customizing adjusting individual needs. Its further development can enable researchers industries significantly enhance the efficiency of dairy processing while providing valuable insights into field. This paper presents an overview role machine industry its potential improve processing. We performed systematic search for articles published between January 2003 2023 related products highlighted algorithms used. 48 studies are discussed assist identifying best methods that could be applied their field relevant ideas future research directions. Moreover, step-by-step guide process, including classification different algorithms, provided. review focuses on state-of-the-art applications milk transformation other products, but it also perspectives conclusions. The study serves as individuals interested about or getting involved with ML.
Язык: Английский
Процитировано
13
Graefe s Archive for Clinical and Experimental Ophthalmology, Год журнала: 2024, Номер unknown
Опубликована: Сен. 15, 2024
Язык: Английский
Процитировано
11
SSRN Electronic Journal, Год журнала: 2024, Номер unknown
Опубликована: Янв. 1, 2024
This paper provides a review of recent publications and working papers on ChatGPT related Large Language Models (LLMs) in accounting finance. The aim is to understand the current state research these two areas identify potential opportunities for future inquiry. We three common themes from earlier studies. first theme focuses applications LLMs various fields second utilizes as new tool by leveraging their capabilities such classification, summarization, text generation. third investigates implications LLM adoption finance professionals, well organizations sectors. While studies provide valuable insights, they leave many important questions unanswered or partially addressed. propose venues further exploration technical guidance researchers seeking employ research.
Язык: Английский
Процитировано
8
International Journal of Medical Informatics, Год журнала: 2024, Номер 188, С. 105501 - 105501
Опубликована: Май 26, 2024
Recent enhancements in Large Language Models (LLMs) such as ChatGPT have exponentially increased user adoption. These models are accessible on mobile devices and support multimodal interactions, including conversations, code generation, patient image uploads, broadening their utility providing healthcare professionals with real-time for clinical decision-making. Nevertheless, many authors highlighted serious risks that may arise from the adoption of LLMs, principally related to safety alignment ethical guidelines. To address these challenges, we introduce a novel methodological approach designed assess specific feasibility adopting LLMs within area, focus nursing, evaluating performance thereby directing choice. Emphasizing LLMs' adherence scientific advancements, this prioritizes care personalization, according "Organization Economic Co-operation Development" frameworks responsible AI. Moreover, its dynamic nature is adapt future evolutions LLMs. Through integrating advanced multidisciplinary knowledge, Nursing Informatics, aided by prospective literature review, seven key domains evaluation items were identified follows: State Art Alignment & Safety. Focus, Accuracy Management Prompt Ambiguity. Data Integrity, Security, Ethics Sustainability, accordance OECD Recommendations Responsible Temporal Variability Responses (Consistency) Adaptation standardized terminology Classifications professionals. General Capabilities: Post User Feedback Self-Evolution Capability Organization Chapters. Ability Drive Evolution Healthcare. Nine state art evaluated using methodology oncology nursing decision-making, producing preliminary results. Gemini Advanced, Anthropic Claude 3 4 achieved minimum score Safety domain classification "recommended", being also endorsed across all domains. LLAMA 70B 3.5 classified "usable high caution." Others unusable domain. The identification recommended LLM combined critical, prudent, integrative use, can decision-making processes.
Язык: Английский
Процитировано
8
IEEE Access, Год журнала: 2024, Номер unknown, С. 1 - 1
Опубликована: Янв. 1, 2024
This paper explores the dual role of Large Language Models (LLMs) in context online misinformation and disinformation. In today's digital landscape, where internet social media facilitate rapid dissemination information, discerning between accurate content falsified information presents a formidable challenge. Misinformation, often arising unintentionally, disinformation, crafted deliberately, are at forefront this LLMs such as OpenAI's GPT-4, equipped with advanced language generation abilities, present double-edged sword scenario. While they hold promise combating by fact-checking detecting LLM-generated text, their ability to generate realistic, contextually relevant text also poses risks for creating propagating misinformation. Further, plagued many problems biases, knowledge cutoffs, hallucinations, which may further perpetuate The outlines historical developments detection how it affects consumption, especially among youth, introduces applications various domains. It then critically analyzes potential counter disinformation sensitive topics healthcare, COVID-19, political agendas. discusses mitigation strategies, ethical considerations, regulatory measures, summarizing previous methods proposing future research direction toward leveraging benefits while minimizing misuse risks. concludes acknowledging powerful tools significant implications both spreading age.
Язык: Английский
Процитировано
8
Indian Journal of Anaesthesia, Год журнала: 2024, Номер 68(7), С. 631 - 636
Опубликована: Июнь 6, 2024
Background and Aims: Artificial intelligence (AI) chatbots like Conversational Generative Pre-trained Transformer (ChatGPT) have recently created much buzz, especially regarding patient education. Such informed patients understand adhere to the management get involved in shared decision making. The accuracy understandability of generated educational material are prime concerns. Thus, we compared ChatGPT with traditional information leaflets (PILs) about chronic pain medications. Methods: Patients' frequently asked questions were from PILs available on official websites British Pain Society (BPS) Faculty Medicine. Eight blinded annexures prepared for evaluation, consisting BPS AI-generated materials structured similar by ChatGPT. authors performed a comparative analysis assess materials’ readability, emotional tone, accuracy, actionability, understandability. Readability was measured using Flesch Reading Ease (FRE), Gunning Fog Index (GFI), Flesch-Kincaid Grade Level (FKGL). Sentiment determined tone. An expert panel evaluated completeness. Actionability assessed Patient Education Materials Assessment Tool. Results: Traditional generally exhibited higher readability ( P values < 0.05), [mean (standard deviation)] FRE [62.25 (1.6) versus 48 (3.7)], GFI [11.85 (0.9) 13.65 (0.7)], FKGL [8.33 (0.5) 10.23 (0.5)] but varied tones, often negative, more positive sentiments ChatGPT-generated texts. Accuracy completeness did not significantly differ between two. scores comparable. Conclusion: While AI offer efficient delivery, ensuring patient-centeredness remains crucial. It is imperative balance innovation evidence-based practice.
Язык: Английский
Процитировано
8
Ethics and Information Technology, Год журнала: 2024, Номер 26(3)
Опубликована: Июль 17, 2024
Язык: Английский
Процитировано
8
Knowledge-Based Systems, Год журнала: 2025, Номер unknown, С. 112965 - 112965
Опубликована: Янв. 1, 2025
Язык: Английский
Процитировано
1
Frontiers in Education, Год журнала: 2024, Номер 9
Опубликована: Май 9, 2024
The use of and research on the large language model (LLM) Generative Pretrained Transformer (GPT) is growing steadily, especially in mathematics education. As students teachers worldwide increasingly this AI for teaching learning mathematics, question quality generated output becomes important. Consequently, study evaluates AI-supported mathematical problem solving with different GPT versions when LLM subjected to prompt techniques. To assess educational (content related process related) LLM’s output, we facilitated four techniques investigated their effects validations ( N = 1,080) using three problem-based tasks. Subsequently, human raters scored output. results showed that content-related was not significantly affected by various across versions. However, certain techniques, particular Chain-of-Thought Ask-me-Anything, notably improved process-related quality.
Язык: Английский
Процитировано
7
Medicina, Год журнала: 2024, Номер 60(6), С. 957 - 957
Опубликована: Июнь 8, 2024
Background and Objectives: Large language models (LLMs) are emerging as valuable tools in plastic surgery, potentially reducing surgeons’ cognitive loads improving patients’ outcomes. This study aimed to assess compare the current state of two most common readily available LLMs, Open AI’s ChatGPT-4 Google’s Gemini Pro (1.0 Pro), providing intraoperative decision support reconstructive surgery procedures. Materials Methods: We presented each LLM with 32 independent scenarios spanning 5 utilized a 5-point 3-point Likert scale for medical accuracy relevance, respectively. determined readability responses using Flesch–Kincaid Grade Level (FKGL) Flesch Reading Ease (FRE) score. Additionally, we measured models’ response time. compared performance Mann–Whitney U test Student’s t-test. Results: significantly outperformed accurate (3.59 ± 0.84 vs. 3.13 0.83, p-value = 0.022) relevant (2.28 0.77 1.88 0.032) responses. Alternatively, provided more concise readable responses, an average FKGL (12.80 1.56) lower than ChatGPT-4′s (15.00 1.89) (p < 0.0001). However, there was no difference FRE scores 0.174). Moreover, Gemini’s time faster (8.15 1.42 s) ChatGPT’-4′s (13.70 2.87 Conclusions: Although both demonstrated potential tools. Nevertheless, their inconsistency across different procedures underscores need further training optimization ensure reliability decision-support
Язык: Английский
Процитировано
7