Lecture notes in computer science, Год журнала: 2024, Номер unknown, С. 148 - 159
Опубликована: Янв. 1, 2024
Язык: Английский
Lecture notes in computer science, Год журнала: 2024, Номер unknown, С. 148 - 159
Опубликована: Янв. 1, 2024
Язык: Английский
iScience, Год журнала: 2024, Номер 27(5), С. 109713 - 109713
Опубликована: Апрель 23, 2024
This study systematically reviewed the application of large language models (LLMs) in medicine, analyzing 550 selected studies from a vast literature search. LLMs like ChatGPT transformed healthcare by enhancing diagnostics, medical writing, education, and project management. They assisted drafting documents, creating training simulations, streamlining research processes. Despite their growing utility diagnosis improving doctor-patient communication, challenges persisted, including limitations contextual understanding risk over-reliance. The surge LLM-related indicated focus on patient but highlighted need for careful integration, considering validation, ethical concerns, balance with traditional practice. Future directions suggested multimodal LLMs, deeper algorithmic understanding, ensuring responsible, effective use healthcare.
Язык: Английский
Процитировано
79International Journal of Data Science and Analytics, Год журнала: 2024, Номер unknown
Опубликована: Июль 1, 2024
Язык: Английский
Процитировано
23Journal of Transcultural Communication, Год журнала: 2024, Номер unknown
Опубликована: Сен. 16, 2024
Abstract This paper delves into the intricate relationship between Large Language Models (LLMs) and cultural bias. It underscores significant impact LLMs can have on shaping a more equitable culturally sensitive digital landscape, while also addressing challenges that arise when integrating these powerful AI tools. The emphasizes immense significance of in contemporary research applications, underpinning many systems algorithms. However, their potential role perpetuating or mitigating bias remains pressing issue warranting extensive analysis. Cultural stems from various intertwined factors; following analysis categorizes three dimensions: data quality, algorithm design, user interaction dynamics. Furthermore, impacts identity linguistic diversity are scrutinized, highlighting interplay technology culture. advocates responsible development, outlining mitigation strategies such as ethical guidelines, diverse training data, feedback mechanisms, transparency measures. In conclusion, is not solely problem but presents an opportunity. enhance our awareness critical understanding own biases fostering curiosity respect for perspectives.
Язык: Английский
Процитировано
8Communications Materials, Год журнала: 2024, Номер 5(1)
Опубликована: Дек. 19, 2024
Automated data extraction from materials science literature at scale using artificial intelligence and natural language processing techniques is critical to advance discovery. However, this process for large spans of text continues be a challenge due the specific nature styles scientific manuscripts. In study, we present framework automatically extract polymer-property full-text journal articles commercially available (GPT-3.5) open-source (LlaMa 2) models (LLM), in tandem with named entity recognition (NER)-based MaterialsBERT model. Leveraging corpus ~ 2.4 million full articles, our method successfully identified processed around 681,000 polymer-related resulting over one records corresponding 24 properties 106,000 unique polymers. We additionally conducted an extensive evaluation performance associated costs LLMs used extraction, compared NER suggest methodologies optimize costs, provide insights on effective inference via in-context few-shots learning, illuminate gaps opportunities future studies utilizing polymer science. The extracted has been made publicly wider community Polymer Scholar website. key Here, authors models.
Язык: Английский
Процитировано
6Опубликована: Апрель 22, 2024
This research introduces an innovative AI-driven precision agriculture system, leveraging YOLOv8 for disease identification and Retrieval Augmented Generation (RAG) context-aware diagnosis. Focused on addressing the challenges of diseases affecting coffee production sector in Karnataka, The system integrates sophisticated object detection techniques with language models to address inherent constraints associated Large Language Models (LLMs). Our methodology not only tackles issue hallucinations LLMs, but also dynamic remediation strategies. Real-time monitoring, collaborative dataset expansion, organizational involvement ensure system's adaptability diverse agricultural settings. effect suggested extends beyond automation, aiming secure food supplies, protect livelihoods, promote eco-friendly farming practices. By facilitating precise identification, contributes sustainable environmentally conscious agriculture, reducing reliance pesticides. Looking future, project envisions continuous development RAG-integrated systems, emphasizing scalability, reliability, usability. strives be a beacon positive change aligning global efforts toward technologically enhanced production.
Язык: Английский
Процитировано
4Multiple Sclerosis Journal, Год журнала: 2024, Номер unknown
Опубликована: Сен. 23, 2024
Use of techniques derived from generative artificial intelligence (AI), specifically large language models (LLMs), offer a transformative potential on the management multiple sclerosis (MS). Recent LLMs have exhibited remarkable skills in producing and understanding human-like texts. The integration AI imaging applications deployment foundation for classification prognosis disease course, including disability progression even therapy response, received considerable attention. However, use within context MS remains relatively underexplored. to support several activities related management. Clinical decision systems could help selecting proper disease-modifying therapies; AI-based tools leverage unstructured real-world data research or virtual tutors may provide adaptive education materials neurologists people with foreseeable future. In this focused review, we explore practical across continuum as an initial scope future analyses, reflecting regulatory hurdles indispensable role human supervision.
Язык: Английский
Процитировано
4Опубликована: Фев. 7, 2025
The recent developments in artificial intelligence (AI), particularly light of the impressive capabilities transformer-based Large Language Models (LLMs), have reignited discussion cognitive science regarding whether computational devices could possess semantic understanding or they are merely mimicking human intelligence. Recent research has highlighted limitations LLMs’ reasoning, suggesting that gap between mere symbol manipulation (syntax) and deeper (semantics) remains wide open. While LLMs overcome certain aspects grounding problem through feedback, still lack true understanding, struggling with common-sense reasoning abstract thinking. This paper argues while adding sensory inputs embodying AI sensorimotor integration environment might enhance its ability to connect symbols real-world meaning, this alone would not close syntax semantics. True meaning-making also requires a connection subjective experience, which current lacks. path AGI must address fundamental relationship manipulation, data processing, pattern matching, probabilistic best guesses knowledge conscious experience. A transition from can occur only if it possesses is closely tied understanding. Recognition furnish new insights into longstanding practical philosophical questions for theories biology provide more meaningful tests than Turing test.
Язык: Английский
Процитировано
0Autonomous Agents and Multi-Agent Systems, Год журнала: 2025, Номер 39(1)
Опубликована: Март 7, 2025
Язык: Английский
Процитировано
0Mining Metallurgy & Exploration, Год журнала: 2025, Номер unknown
Опубликована: Март 27, 2025
Язык: Английский
Процитировано
0Опубликована: Апрель 2, 2025
The recent developments in artificial intelligence (AI), particularly light of the impressive capabilities transformer-based Large Language Models (LLMs), have reignited discussion cognitive science regarding whether computational devices could possess semantic understanding or they are merely mimicking human intelligence. Recent research has highlighted limitations LLMs’ reasoning, suggesting that gap between mere symbol manipulation (syntax) and deeper (semantics) remains wide open. While LLMs overcome certain aspects grounding problem through feedback, still lack true understanding, struggling with common-sense reasoning abstract thinking. This paper argues while adding sensory inputs embodying AI sensorimotor integration environment might enhance its ability to connect symbols real-world meaning, this alone would not close syntax semantics. True meaning-making also requires a connection subjective experience, which current lacks. path AGI must address fundamental relationship manipulation, data processing, pattern matching, probabilistic best guesses knowledge conscious experience. A transition from can occur only if it possesses is closely tied understanding. Recognition furnish new philosophical insights into longstanding practical questions for theories biology provide more meaningful tests than Turing test.
Язык: Английский
Процитировано
0