Log in

Relevant bibliographies by topics / OpenAI Source / Journal articles

To see the other types of publications on this topic, follow the link: OpenAI Source.

Journal articles on the topic 'OpenAI Source'

Author: Grafiati

Published: 2 June 2025

Last updated: 31 July 2025

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Consult the top 50 journal articles for your research on the topic 'OpenAI Source.'

Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.

You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.

Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.

1

Diara, Filippo. "Open Source HBIM and OpenAI: Review and New Analyses on LLMs Integration." Heritage 8, no. 5 (2025): 149. https://doi.org/10.3390/heritage8050149.

Full text

Abstract:

This work concentrates on an experimental project for the integration of Large Language Models (LLMs) inside a Historic Building Information Modeling (HBIM) workflow. In particular, this evaluation was carried out by using open source solutions as concerns parametric modeling of BIM elements. This experimental test focuses on how Python scripts, generated by AI agents, can create parametric models for HBIM purposes and archaeology: starting from the archaeological plan, the parametric modeling of the Parthenon temple was carried out via a text-to-BIM workflow based on OpenAI and open source to

APA, Harvard, Vancouver, ISO, and other styles

2

Doroshenko, A. Y., and I. Z. Achour. "Application of neuro evolution tools in automation of technical control systems." PROBLEMS IN PROGRAMMING, no. 1 (March 2021): 016–25. http://dx.doi.org/10.15407/pp2021.01.016.

Full text

Abstract:

Reinforced learning is a field of machine learning based on how software agents should perform actions in the environment to maximize the concept of cumulative reward. This paper proposes a new application of machine reinforcement learning techniques in the form of neuro-evolution of augmenting topologies to solve control automation problems using modeling control problems of technical systems. Key application components include OpenAI Gym toolkit for develop-ing and comparing reinforcement learn-ing algorithms, full-fledged open-source implementation of the NEAT genetic al-gorithm called Shar

APA, Harvard, Vancouver, ISO, and other styles

3

Roy, Josh, and George D. Konidaris. "Visual Transfer For Reinforcement Learning Via Wasserstein Domain Confusion." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 11 (2021): 9454–62. http://dx.doi.org/10.1609/aaai.v35i11.17139.

Full text

Abstract:

We introduce Wasserstein Adversarial Proximal Policy Optimization (WAPPO), a novel algorithm for visual transfer in Reinforcement Learning that explicitly learns to align the distributions of extracted features between a source and target task. WAPPO approximates and minimizes the Wasserstein-1 distance between the distributions of features from source and target domains via a novel Wasserstein Confusion objective. WAPPO outperforms the prior state-of-the-art in visual transfer and successfully transfers policies across Visual Cartpole and both the easy and hard settings of of 16 OpenAI Procge

APA, Harvard, Vancouver, ISO, and other styles

4

Alzubaidi, Khairi. "Foreword." Arab World English Journal 1, no. 1 (2024): 3. http://dx.doi.org/10.24093/awej/chatgpt.23.

Full text

Abstract:

As technology advances, there are growing arguments about artificial intelligence, which is still controversial, with both welcome and pessimistic views regarding its role in the future of human life. What was revealed about the development of artificial intelligence is considered very simple in the eyes of specialists and observers, especially in areas that have not been explored, and this constitutes a source of fear for many. The vast leaps witnessed in recent years in the field of artificial intelligence have become a source of anxiety for most people, especially those working in instituti

APA, Harvard, Vancouver, ISO, and other styles

5

Palkowski, Marek, and Mateusz Gruzewski. "GPT-Driven Source-to-Source Transformation for Generating Compilable Parallel CUDA Code for Nussinov’s Algorithm." Electronics 13, no. 3 (2024): 488. http://dx.doi.org/10.3390/electronics13030488.

Full text

Abstract:

Designing automatic optimizing compilers is an advanced engineering process requiring a great deal of expertise, programming, testing, and experimentation. Maintaining the approach and adapting it to evolving libraries and environments is a time-consuming effort. In recent years, OpenAI has presented the GPT model, which is designed for many fields like computer science, image processing, linguistics, and medicine. It also supports automatic programming and translation between programming languages, as well as human languages. This article will verify the usability of the commonly known LLM mo

APA, Harvard, Vancouver, ISO, and other styles

6

Andhov (Horváthová), Alexandra. "OpenAI’s Transformation: From a Non-profit to a 157 Billion Valuation." Business Law Review 46, Issue 1 (2025): 2–11. https://doi.org/10.54648/bula2025003.

Full text

Abstract:

p class="MsoNormal"span style="font-size:10.0pt;line-height:107%;font-family: "AdvOTecfccdcf_I",sans-serif;mso-bidi-font-family:AdvOTecfccdcf_I"The transformation of OpenAI from its altruistic non-profit origins to a commercially-driven entity valued at over USD 157 billion in October 2024 represents a significant paradigm shift in the artificial intelligence (A)I industry. Established in 2015 with the aim of developing AI for the greater good and providing open-source resources, OpenAI has since pivoted to a profit-generating model, underscored by a strategic partnership withMicrosoft. This e

APA, Harvard, Vancouver, ISO, and other styles

7

Mitra, Roshni, and Parthasarathi Mukhopadhyay. "Machine Learning Applications in Digital Humanities." DESIDOC Journal of Library & Information Technology 43, no. 04 (2023): 219–25. http://dx.doi.org/10.14429/djlit.43.04.19227.

Full text

Abstract:

This research study explores the potential of machine learning tools and techniques to organize knowledge objects pertaining to various aspects of the gender spectrum (LGBTQIA+) in order to address the low-resource features of the LGBTQIA+ knowledge domain in Indian libraries. It aims to develop a semi-automated subject indexing system using an open source machine learning framework (Annif) and deploying the Homosaurus, a domain-specific vocabulary system. It develops programmatically a comprehensive training dataset from open-access bibliographic data sources with the help of data carpentry t

APA, Harvard, Vancouver, ISO, and other styles

8

Zhuo, Kevin Yinkit, Paul Kim, James Kovacic, et al. "Can Artificial Intelligence Treat My Urinary Tract Infections?—Evaluation of Health Information Provided by OpenAI™ ChatGPT on Urinary Tract Infections." Société Internationale d’Urologie Journal 5, no. 2 (2024): 104–7. http://dx.doi.org/10.3390/siuj5020018.

Full text

Abstract:

Urinary tract infections (UTIs) are highly prevalent and have significant implications for patients. As internet-based health information becomes more relied upon, ChatGPT has emerged as a potential source of healthcare advice. In this study, ChatGPT-3.5 was subjected to 16 patient-like UTI queries, with its responses evaluated by a panel of urologists. ChatGPT can address general UTI questions and exhibits some reasoning capacity in specific contexts. Nevertheless, it lacks source verification, occasionally overlooks vital information, and struggles with contextual clinical advice. ChatGPT ho

APA, Harvard, Vancouver, ISO, and other styles

9

Polepaka, Sanjeeva, Varikuppala Prashanth Kumar, S. Umesh Chandra, Hema Nagendra Sri Krishna, and Gaurav Thakur. "Automated Caption Generation for Video Call with Language Translation." E3S Web of Conferences 430 (2023): 01025. http://dx.doi.org/10.1051/e3sconf/202343001025.

Full text

Abstract:

In the modern era, virtual communication between individuals is common. Many people’s lives have been made simpler in a number of circumstances by providing subtitles, generating automated captions for social media videos, and language translation from a source language to a targeted language. Both are included, which offers face-to-face translated captions during video conversations. React is used for application development. To send the data, socket programming is utilized. Context is understood and translated using Google translate API and speech recognition modules. With OpenAI and Whisper

APA, Harvard, Vancouver, ISO, and other styles

10

Li, Baolin, Yankai Jiang, and Devesh Tiwari. "Carbon in Motion: Characterizing Open-Sora on the Sustainability of Generative AI for Video Generation." ACM SIGEnergy Energy Informatics Review 4, no. 5 (2024): 160–65. https://doi.org/10.1145/3727200.3727224.

Full text

Abstract:

The rapid rise of generative AI (GenAI) technologies has brought innovative video generation models like OpenAI's Sora to the forefront, but these advancements come with significant sustainability challenges due to their high carbon footprint. This paper presents a carbon-centric case study on video generation, providing the first systematic investigation into the environmental impact of this technology. By analyzing Open-Sora, an open-source text-to-video model inspired by OpenAI Sora, we identify the iterative diffusion denoising process as the primary source of carbon emissions. Our finding

APA, Harvard, Vancouver, ISO, and other styles

11

Boschee, Pam. "Comments: AI Language Tools Hit the Books . . . and Technical Content?" Journal of Petroleum Technology 75, no. 04 (2023): 8–9. http://dx.doi.org/10.2118/0423-0008-jpt.

Full text

Abstract:

Are you among the millions of ChatGPT users/experimenters around the world? Or impatiently parked on the waitlist? OpenAI launched ChatGPT in late November 2022 with little fanfare. Within a week, the company reported 1 million users. Within the first month, it exceeded 57 million users. Since then, it has been updated several times and a UBS analyst estimated in February that the artificial intelligence (AI) language tool reached 100 million users. The website exceeded 13 million daily visitors as of January. On 1 February, OpenAI announced a ChatGPT Plus monthly subscription plan to give pri

APA, Harvard, Vancouver, ISO, and other styles

12

Stočes, Michal, Jiří Vaněk, Jan Jarolímek, et al. "Agriculture Data Platform – Institutional Data Repository – Selected Aspects." Agris on-line Papers in Economics and Informatics 15, no. 4 (2023): 127–33. http://dx.doi.org/10.7160/aol.2023.150409.

Full text

Abstract:

This paper presents selected aspects of a data platform to store agricultural data. It analyses the key user and system requirements for the data platform. The presented aspects were identified through a literature review, interviews and discussions with selected data experts and researchers and future users of the platform. The following issues of the data platform are discussed in the paper: architecture, data types, data source types, metadata, disciplinary interfaces, data sharing, data reusability, Open Science, FAIR data principles, and further data processing options. Part of the knowle

APA, Harvard, Vancouver, ISO, and other styles

13

Ms., Abinaya Meyyammai Meyyappan, and Kamalajyothini G. Ms. "AI-Generated Content and Copyright Infringement: A Legal Analysis of OpenAI's Practices and Global IPR Challenges." Annual International Journal on Analysis of Contemporary Legal Affairs (AIJACLA) 5 (May 25, 2025): 126–33. https://doi.org/10.5281/zenodo.15514190.

Full text

Abstract:

<em>Generative AI technologies, such as OpenAI’s ChatGPT and DALL·E, are experiencing rapid growth. They have become the force which is disrupting the whole system of traditional intellectual property (IP) and have raised serious questions about authorship, ownership and the violation of rights. This paper is exploring the main challenges and dangers of AI-generated content in the legal and ethical spheres of copyright, trademark, and patent laws, and it explicitly points out the irrevocable weakness of the currently existing IP regimes tailored for human creativity. Focusing on t

APA, Harvard, Vancouver, ISO, and other styles

14

Verma, Aditya A. "Augmenting AI’s Prospects: ChatGPT Future Insights." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 08, no. 04 (2024): 1–5. http://dx.doi.org/10.55041/ijsrem30633.

Full text

Abstract:

An expansion of GPT-3, the big language model ChatGPT was published by OpenAI on November 30, 2022. In real time, the AI chatbot responds to user requests by communicating. The level of natural speaking responses provided by ChatGPT signals a significant change in the way we will utilise AI-generated data in our daily lives. There are several applications for ChatGPT for a student studying software engineering, including assessment preparation, translation, and writing specific source code. Even more difficult parts of scientific writing, including paraphrasing and literature summaries, may be

APA, Harvard, Vancouver, ISO, and other styles

15

Ngo, Thi Thuy An. "The Perception by University Students of the Use of ChatGPT in Education." International Journal of Emerging Technologies in Learning (iJET) 18, no. 17 (2023): 4–19. http://dx.doi.org/10.3991/ijet.v18i17.39019.

Full text

Abstract:

ChatGPT, a generative language model recently created by OpenAI, has drawn a lot of criticism from people all around the world. ChatGPT illustrates both potential opportunities and challenges in education. This study aims to investigate how university students perceive using ChatGPT for learning, including benefits, barriers, and potential solutions. To determine how students felt about using ChatGPT in their learning, a questionnaire was distributed to 200 students via an online survey, and 30 students participated in semi-structured interviews. The research results showed that, in general, s

APA, Harvard, Vancouver, ISO, and other styles

16

Ghazal, Ahmad, Zhiyuan Liang, Sunny Bains, and Hanumath Maduri. "OSSInsight: Scalable GitHub Analysis." Proceedings of the VLDB Endowment 17, no. 12 (2024): 4321–24. http://dx.doi.org/10.14778/3685800.3685865.

Full text

Abstract:

GitHub is a platform hosting code, enabling collaboration, and supporting version control for a global community of over 100 million developers. The need for free tools is crucial for researching open-source software. Based on our research, we found out that existing tools lack real-time GitHub data processing or have limited functionalities. This demonstration presents OSSInsight, an open source tool for researching and analyzing GitHub repositories. We first present the architecture of the tool including its access to nearly 7 billion archived & real time data and how it is powered by Ti

APA, Harvard, Vancouver, ISO, and other styles

17

Маковейчук, К. А., А. В. Олифиров, Г. М. Деменчук та Я. Т. Маковейчук. "Применение больших языковых моделей для разметки наборов данных в задачах обработки естественного языка". Международный научный журнал "Современные информационные технологии и ИТ-образование" 19, № 3 (2023): 598–606. https://doi.org/10.25559/sitito.019.202303.598-606.

Full text

Abstract:

В статье предложена методика использования больших языковых моделей компании OpenAI для разметки текстовых данных через доступный программный интерфейс. Разработанная методика является первым этапом решения задачи из категории обработки естественного языка. Задача в целом состоит в классификации курсов, которые могут быть многоклассовыми или с множественными метками, с помощью алгоритмов машинного обучения. Предоставленные слабоструктурированные данные о курсах включали большое количество различных колонок и имели размер 275811 строк, однако категории, подкатегории и предметы не были определен

APA, Harvard, Vancouver, ISO, and other styles

18

Spennemann, Dirk H. R. "The Origins and Veracity of References ‘Cited’ by Generative Artificial Intelligence Applications: Implications for the Quality of Responses." Publications 13, no. 1 (2025): 12. https://doi.org/10.3390/publications13010012.

Full text

Abstract:

The public release of ChatGPT in late 2022 has resulted in considerable publicity and has led to widespread discussion of the usefulness and capabilities of generative Artificial intelligence (Ai) language models. Its ability to extract and summarise data from textual sources and present them as human-like contextual responses makes it an eminently suitable tool to answer questions users might ask. Expanding on a previous analysis of the capabilities of ChatGPT3.5, this paper tested what archaeological literature appears to have been included in the training phase of three recent generative Ai

APA, Harvard, Vancouver, ISO, and other styles

19

Maylott, Paige, Shaminder Dhillon, Dina Brooks, and Sarah Wojkowski. "Integration of Artificial Intelligence (AI) into the Data Extraction Phase of a Scoping Review." Journal of Innovative Research 3, no. 1 (2025): 89–94. https://doi.org/10.54536/jir.v3i1.3946.

Full text

Abstract:

This paper describes how artificial intelligence (AI) was used to assist with the data extraction phase of a scoping review, specifically comparing different AI models and the accuracy of AI-assisted data extraction compared to human extraction. Scoping reviews map existing literature on a topic and are useful for complex or under-reviewed subjects. Integrating AI, particularly large language models, can enhance processing speed and data analysis. Three models, ChatGPT 3.5 and -4 (both developed by OpenAI) and Copilot (by Microsoft), were compared to identify the best model for AI-assisted dat

APA, Harvard, Vancouver, ISO, and other styles

20

Csereoka, Petra, Bogdan-Ionuţ Roman, Mihai Victor Micea , and Călin-Adrian Popa. "Novel Reinforcement Learning Research Platform for Role-Playing Games." Mathematics 10, no. 22 (2022): 4363. http://dx.doi.org/10.3390/math10224363.

Full text

Abstract:

The latest achievements in the field of reinforcement learning have encouraged the development of vision-based learning methods that compete with human-provided results obtained on various games and training environments. Convolutional neural networks together with Q-learning-based approaches have managed to solve and outperform human players in environments such as Atari 2600, Doom or StarCraft II, but the niche of 3D realistic games with a high degree of freedom of movement and rich graphics remains unexplored, despite having the highest resemblance to real-world situations. In this paper, w

APA, Harvard, Vancouver, ISO, and other styles

21

Meo, Sultan Ayoub. "Chatbot-generative pretrained transformer: Potential role in medical education and clinical settings." Advances in Biomedical and Health Sciences 3, no. 1 (2024): 1–4. http://dx.doi.org/10.4103/abhs.abhs_89_23.

Full text

Abstract:

ABSTRACT The chatbot-generative pretrained transformer (ChatGPT) was developed as a prototype by OpenAI on November 30, 2022. Artificial Intelligence software is designed to generate and enhance dialog and discussion among users. ChatGPT has attracted significant attention from the scientific community, physicians, and the public. It provides appropriate answers and explanations for various subjects. ChatGPT is a useful tool in scientific writing, generating essays, editorials, blogs, brief revisions, providing explanations, and generating initial drafts of articles. It uses multiple choice qu

APA, Harvard, Vancouver, ISO, and other styles

22

Mendonça, Pedro C., Filipe Quintal, and Fábio Mendonça. "Evaluating LLMs for Automated Scoring in Formative Assessments." Applied Sciences 15, no. 5 (2025): 2787. https://doi.org/10.3390/app15052787.

Full text

Abstract:

The increasing complexity and scale of modern education have revealed the shortcomings of traditional grading methods in providing consistent and scalable assessments. Advancements in artificial intelligence have positioned Large Language Models (LLMs) as robust solutions for automating grading tasks. This study systematically compared the grading performance of an open-source LLM (LLaMA 3.2) and a premium LLM (OpenAI GPT-4o) against human evaluators across diverse question types in the context of a computer programming subject. Using detailed rubrics, the study assessed the alignment between

APA, Harvard, Vancouver, ISO, and other styles

23

Tamez, Valdemar, and Gbolahan Solomon Osho. "AI Disruption at Scale: DeepSeek’s Open-Source Model and Its Macroeconomic Impact on Markets, Labor, and Global Growth." International Journal of Business Management and Finance Research 8, no. 3 (2025): 1–11. https://doi.org/10.53935/26415313.v8i3.398.

Full text

Abstract:

This study explores the macroeconomic implications of DeepSeek, a Chinese artificial intelligence (AI) startup that disrupted the global AI landscape through the release of DeepSeek-R1, an open-source, cost-efficient large language model. Developed with significantly lower training costs and released under an MIT license, DeepSeek’s model rivaled proprietary offerings from Western firms like OpenAI and Google, triggering financial market turbulence and investor realignment. The study analyzes how DeepSeek’s innovation challenged prevailing norms in AI infrastructure, democratized access to adv

APA, Harvard, Vancouver, ISO, and other styles

24

Landgraf, Christian, Bernd Meese, Michael Pabst, Georg Martius, and Marco F. Huber. "A Reinforcement Learning Approach to View Planning for Automated Inspection Tasks." Sensors 21, no. 6 (2021): 2030. http://dx.doi.org/10.3390/s21062030.

Full text

Abstract:

Manual inspection of workpieces in highly flexible production facilities with small lot sizes is costly and less reliable compared to automated inspection systems. Reinforcement Learning (RL) offers promising, intelligent solutions for robotic inspection and manufacturing tasks. This paper presents an RL-based approach to determine a high-quality set of sensor view poses for arbitrary workpieces based on their 3D computer-aided design (CAD). The framework extends available open-source libraries and provides an interface to the Robot Operating System (ROS) for deploying any supported robot and

APA, Harvard, Vancouver, ISO, and other styles

25

Louw, Cobus, Louwrens Labuschagne, and Tiffany Woodley. "Comparison of Reinforcement Learning Agents Applied to Traffic Signal Optimisation." SUMO Conference Proceedings 3 (September 29, 2022): 15–43. http://dx.doi.org/10.52825/scp.v3i.116.

Full text

Abstract:

Traditional methods for traffic signal control at an urban intersection are not effective in controlling traffic flow for dynamic traffic demand which leads to negative environmental, psychological and financial impacts for all parties involved. Urban traffic management is a complex problem with multiple factors effecting the control of traffic flow. With recent advancements in machine learning (ML), especially reinforcement learning (RL), there is potential to solve this problem. The idea is to allow an agent to learn optimal behaviour to maximise specific metrics through trial and error. In

APA, Harvard, Vancouver, ISO, and other styles

26

Li, Yue, Bohan Liu, Ting Zhang, et al. "A Knowledge Enhanced Large Language Model for Bug Localization." Proceedings of the ACM on Software Engineering 2, FSE (2025): 1914–36. https://doi.org/10.1145/3729356.

Full text

Abstract:

A significant number of bug reports are generated every day as software systems continue to develop. Large Language Models (LLMs) have been used to correlate bug reports with source code to locate bugs automatically. The existing research has shown that LLMs are effective for bug localization and can increase software development efficiency. However, these studies still have two limitations. First, these models fail to capture context information about bug reports and source code. Second, these models are unable to understand the domain-specific expertise inherent to particular projects, such

APA, Harvard, Vancouver, ISO, and other styles

27

Arkhipova, Zoya, and Valery Staver. "Comparative Analysis of Speech Transcription Technologies for the Digitalization of Technical Support Services." System Analysis & Mathematical Modeling 7, no. 1 (2025): 5–16. https://doi.org/10.17150/2713-1734.2025.7(1).5-16.

Full text

Abstract:

This article is dedicated to the application of neural network technologies to enhance the efficiency and quality of technical support services. The use of speech transcription technologies is becoming increasingly relevant due to the rising demands for high-quality information processing in various fields. The study examines the main approaches to speech transcription, including classical methods, deep learning-based solutions, hybrid approaches, as well as commercial and open-source tools. The research aims to conduct a comparative analysis of modern transcription systems to select and subse

APA, Harvard, Vancouver, ISO, and other styles

28

Ismantara, Stefany, and Wilma Silalahi. "The Lawfulness of Using Inventions for Generative AI Training : A Case Study of a US Lawsuit against OpenAI and Perplexity AI." JUSTISI 11, no. 1 (2024): 127–50. https://doi.org/10.33506/js.v11i1.3871.

Full text

Abstract:

Copyright protection in Indonesia is governed by Law No. 28 of 2014 (Law 28/2014), encompassing moral and economic rights. This law imposes limitations on the use of works for education, law enforcement, or technological development as long as such use does not harm the legitimate interests of the rightholder. The development of generative AI (GAI) poses challenges in determining the legality of using copyrighted works for GAI training. This study examines copyright regulations concerning GAI through normative, conceptual, and comparative legal approaches, including case studies on lawsuits ag

APA, Harvard, Vancouver, ISO, and other styles

29

Żmudka, Karol, Aleksandra Spychał, Błażej Ochman, Łukasz Popowicz, Patrycja Piłat, and Jerzy Jaroszewicz. "ChatGPT – a tool for assisted studying or a source of misleading medical information? AI performance on Polish Medical Final Examination." Annales Academiae Medicae Silesiensis 78 (April 16, 2024): 94–103. http://dx.doi.org/10.18794/aams/176450.

Full text

Abstract:

WstępChatGPT jest modelem językowym stworzonym przez OpenAI, który może udzielać odpowiedzi na zapytania użytkownika, generując tekst na podstawie otrzymanych danych. Celem pracy była ocena wyników działania ChatGPT na polskim Lekarskim Egzaminie Końcowym (LEK) oraz czynników wpływających na odsetek prawidłowych odpowiedzi. Ponadto zbadano zdolność chatbota do podawania poprawnego i wnikliwego wyjaśnienia.Materiał i metodyWprowadzono 591 pytań z dystraktorami z bazy LEK do interfejsu ChatGPT (wersja 13 lutego – 14 marca). Porównano wyniki z kluczem odpowiedzi i przeanalizowano podane wyjaśnien

APA, Harvard, Vancouver, ISO, and other styles

30

Șorecău, Mirela, and Emil Șorecău. "An Alternative Application to CHATGPT that Uses Reliable Sources to Enhance the Learning Process." International conference KNOWLEDGE-BASED ORGANIZATION 29, no. 3 (2023): 113–19. http://dx.doi.org/10.2478/kbo-2023-0084.

Full text

Abstract:

Abstract ChatGPT is a type of language model that uses machine learning algorithms to generate responses to natural language input. Its advanced technology can revolutionize the way humans interact with machines by creating more natural and intuitive communication. However, the accuracy of ChatGPT’s responses may be compromised by biased or inaccurate data, which highlights the importance of carefully evaluating its output. Furthermore, early versions of ChatGPT were found to produce academic papers with missing references, which may compromise the credibility of research in the academic publi

APA, Harvard, Vancouver, ISO, and other styles

31

Moise, Alexander, Adam Centomo-Bozzo, Ostap Orishchak, Mohammed K. Alnoury, and Sam J. Daniel. "Can ChatGPT Guide Parents on Tympanostomy Tube Insertion?" Children 10, no. 10 (2023): 1634. http://dx.doi.org/10.3390/children10101634.

Full text

Abstract:

Background: The emergence of ChatGPT, a state-of-the-art language model developed by OpenAI, has introduced a novel avenue for patients to seek medically related information. This technology holds significant promise in terms of accessibility and convenience. However, the use of ChatGPT as a source of accurate information enhancing patient education and engagement requires careful consideration. The objective of this study was to assess the accuracy and reliability of ChatGPT in providing information on the indications and management of complications post-tympanostomy, the most common pediatri

APA, Harvard, Vancouver, ISO, and other styles

32

Taeb, Maryam, Hongmei Chi, and Shonda Bernadin. "Assessing the Effectiveness and Security Implications of AI Code Generators." Journal of The Colloquium for Information Systems Security Education 11, no. 1 (2024): 6. http://dx.doi.org/10.53735/cisse.v11i1.180.

Full text

Abstract:

Students, especially those outside the field of cybersecurity, are increasingly turning to Large Language Model (LLM)-based generative AI tools for coding assistance. These AI code generators provide valuable support to developers by generating code based on provided input and instructions. However, the quality and accuracy of the generated code can vary, depending on factors such as task complexity, the clarity of instructions, and the model’s familiarity with the programming language. Additionally, these generated codes may inadvertently utilize vulnerable built-in functions, potentially lea

APA, Harvard, Vancouver, ISO, and other styles

33

Teterevenkov, D. L. "EXPERT-ORIENTED METHODS FOR EVALUATING THE QUALITY OF TEXTUAL GENERATION OF LARGE LANGUAGE MODELS." SOFT MEASUREMENTS AND COMPUTING 5, no. 90 (2025): 30–37. https://doi.org/10.36871/2618-9976.2025.05.003.

Full text

Abstract:

This paper is devoted to a systematic analysis of approaches in which human; expert markup remains the key source of reliable judgments. The aim of the paper is to identify the strengths and weaknesses of manual evaluation compared to traditional automatic metrics (BLEU, ROUGE, BERTScore, etc.) and stateoftheart LLM-as-a-Judge schemes. The analysis is based on 2023-2025 research covering both foreign (OpenAI, Anthropic, DeepMind) and domestic instructional benchmarking initiatives. Manual evaluation is confirmed as the "gold standard" due to the consideration of experts' deep sense and common

APA, Harvard, Vancouver, ISO, and other styles

34

Naeem, Zan Ahmad, Mohammad Shahmeer Ahmad, Mohamed Eltabakh, Mourad Ouzzani, and Nan Tang. "RetClean: Retrieval-Based Data Cleaning Using LLMs and Data Lakes." Proceedings of the VLDB Endowment 17, no. 12 (2024): 4421–24. http://dx.doi.org/10.14778/3685800.3685890.

Full text

Abstract:

Large language models (LLMs) have shown great potential in data cleaning, which is a fundamental task in all modern applications. In this demo proposal, we demonstrate that indeed LLMs can assist in data cleaning, e.g., filling in missing values in a data table, through different approaches. For example, cloud-based non-private LLMs, e.g., OpenAI GPT family or Google Gemini, can assist in cleaning non-private datasets that encompass world-knowledge information (Scenario 1). However, such LLMs may struggle with datasets that they have never encountered before, e.g., local enterprise data, or wh

APA, Harvard, Vancouver, ISO, and other styles

35

Wahyuni, Nur, and Nabila Yasmin. "Peran Teknologi ChatGPT dalam Optimalisasi Layanan Referensi bagi Mahasiswa di Perpustakaan Universitas Prima Indonesia." Tik Ilmeu : Jurnal Ilmu Perpustakaan dan Informasi 8, no. 2 (2024): 163–70. https://doi.org/10.29240/tik.v8i2.10840.

Full text

Abstract:

The rapid development of information and communication technology provides recommendations for libraries to optimize reference services to remain relevant and effective for users. One of the latest technologies that can be utilized is ChatGPT. ChatGPT is a large language model developed by OpenAI. This research aims to explore the role of ChatGPT technology in optimizing reference services for students at Prima Indonesia University Library. This study also seeks to identify the factors influencing the utilization of ChatGPT technology by students in accessing reference services. This research

APA, Harvard, Vancouver, ISO, and other styles

36

Nuha, Moch Syihabudin, Usrotun Diniyah, Mario Martin Taneo, Nur Hidayah, and Yuliati Hotifah. "Utilization of Artificial Intelligence Technology in Research." Jurnal Genesis Indonesia 3, no. 03 (2024): 129–42. https://doi.org/10.56741/jgi.v3i03.714.

Full text

Abstract:

The era of the industrial revolution has entered its peak in 5.0 which is an era where humans coexist full of technology. One of them is artificial intelligence and the products it produces such as ChatGPT, OpenAI, and artificial intelligence in other fields. In this era, humans will be given all kinds of conveniences from technology. The search for truth can be done quickly but less accurately. Artificial intelligence uses big data that will continue to be filled with various knowledge so that in the end intelligence can be utilized properly. The use of artificial intelligence technology in r

APA, Harvard, Vancouver, ISO, and other styles

37

Davis, Timothy, Borna Guevel, Kartik Logishetty, Alastair Dick, and Jonathan Hutt. "EVALUATING LARGE LANGUAGE MODELS IN PATIENT EDUCATION: A COMPARATIVE ANALYSIS OF CHATGPT AND GOOGLE GEMINI IN ADDRESSING FREQUENTLY ASKED QUESTIONS IN PERIACETABULAR OSTEOTOMY." Orthopaedic Proceedings 107-B, SUPP_2 (2025): 40. https://doi.org/10.1302/1358-992x.2025.2.040.

Full text

Abstract:

Large language models (LLMs) are rapidly gaining traction as sources of information across various fields, including healthcare. As patients may increasingly turn to these models for health-related inquiries, it becomes necessary to assess the accuracy and reliability of their responses. This study evaluates the performance of two leading LLMs, ChatGPT (OpenAI) and Google Gemini (Google DeepMind), in addressing common patient questions on periacetabular osteotomy (PAO). PAO procedures are performed on younger patients, a demographic that is more likely to engage with digital tools like LLMs to

APA, Harvard, Vancouver, ISO, and other styles

38

Yu, Danning, Kun Ni, and Yunlong Liu. "Deep Q-Network with Predictive State Models in Partially Observable Domains." Mathematical Problems in Engineering 2020 (July 16, 2020): 1–9. http://dx.doi.org/10.1155/2020/1596385.

Full text

Abstract:

While deep reinforcement learning (DRL) has achieved great success in some large domains, most of the related algorithms assume that the state of the underlying system is fully observable. However, many real-world problems are actually partially observable. For systems with continuous observation, most of the related algorithms, e.g., the deep Q-network (DQN) and deep recurrent Q-network (DRQN), use history observations to represent states; however, they often make computation-expensive and ignore the information of actions. Predictive state representations (PSRs) can offer a powerful framewor

APA, Harvard, Vancouver, ISO, and other styles

39

Sorokina, Svetlana. "Exploring Automated Summarization: From Extraction to Abstraction." Vestnik Volgogradskogo gosudarstvennogo universiteta. Serija 2. Jazykoznanije 23, no. 5 (2024): 47–59. https://doi.org/10.15688/jvolsu2.2024.5.4.

Full text

Abstract:

This paper provides a review of AI-powered automated summarization models, with a focus on two principal approaches: extractive and abstractive. The study aims to evaluate the capabilities of these models in generating concise yet meaningful summaries and analyze their lexical proficiency and linguistic fluidity. The compression rates are assessed using quantitative metrics such as page, word, and character counts, while language fluency is described in terms of ability to manipulate grammar and lexical patterns without compromising meaning and content. The study draws on a selection of scient

APA, Harvard, Vancouver, ISO, and other styles

40

Shacklett, Brennan, Luc Guy Rosenzweig, Zhiqiang Xie, et al. "An Extensible, Data-Oriented Architecture for High-Performance, Many-World Simulation." ACM Transactions on Graphics 42, no. 4 (2023): 1–13. http://dx.doi.org/10.1145/3592427.

Full text

Abstract:

Training AI agents to perform complex tasks in simulated worlds requires millions to billions of steps of experience. To achieve high performance, today's fastest simulators for training AI agents adopt the idea of batch simulation: using a single simulation engine to simultaneously step many environments in parallel. We introduce a framework for productively authoring novel training environments (including custom logic for environment generation, environment time stepping, and generating agent observations and rewards) that execute as high-performance, GPU-accelerated batched simulators. Our

APA, Harvard, Vancouver, ISO, and other styles

41

Çolakoğlu, Yunus, Ali Ayten, Çağlar Sertkaya, Kağan Toksal, and Serdar Karadağ. "Evaluation of Chat Generative Pretrained Transformer (ChatGPT) Performance in Answering Kidney Transplant Related Questions." New Journal of Urology 20, no. 1 (2025): 21–31. https://doi.org/10.33719/nju1613084.

Full text

Abstract:

Objective: Social media such as (Youtube, Facebook, Instagram, Twitter, etc.) and artificial intelligence (AI) are applications that have become popular in recent years, they are the first resources that patients turn to today. ChatGPT is an AI-powered language model developed by OpenAI and its success on health problems are demonstrated by many studies. In this study, we aimed to evaluate the adequacy of ChatGPT’s answers to questions about kidney transplantation. Material and Methods: Frequently asked questions about kidney transplantation by patients on health forums, websites and social me

APA, Harvard, Vancouver, ISO, and other styles

42

Satyadhar Joshi. "Review of autonomous systems and collaborative AI agent frameworks." International Journal of Science and Research Archive 14, no. 2 (2025): 961–72. https://doi.org/10.30574/ijsra.2025.14.2.0439.

Full text

Abstract:

This paper provides an in-depth review of the latest AI agent frameworks, focusing on the comparison of their features, architectures, and use cases. We examine well-known frameworks such as LangGraph, CrewAI, OpenAI Swarm, AutoGen, and IBM Watsonx.Ai, highlighting their strengths, weaknesses, and applicability to various domains. Additionally, we categorize the frameworks based on their specific use cases, including general-purpose agents, enterprise solutions, and open-source frameworks. The paper emphasizes the importance of selecting the appropriate framework to build autonomous AI systems

APA, Harvard, Vancouver, ISO, and other styles

43

Joshi, Satyadhar. "Review of autonomous systems and collaborative AI agent frameworks." International Journal of Science and Research Archive 14, no. 02 (2025): 961–72. https://doi.org/10.30574/ijsra.2025.14.2.0439.

Full text

Abstract:

This paper provides an in-depth review of the latest AI agent frameworks, focusing on the comparison of their features, architectures, and use cases. We examine well-known frameworks such as LangGraph, CrewAI, OpenAI Swarm, AutoGen, and IBM Watsonx.Ai, highlighting their strengths, weaknesses, and applicability to various domains. Additionally, we categorize the frameworks based on their specific use cases, including general-purpose agents, enterprise solutions, and open-source frameworks. The paper emphasizes the importance of selecting the appropriate framework to build autonomous AI systems

APA, Harvard, Vancouver, ISO, and other styles

44

Ma, Yingwei, Rongyu Cao, Yongchang Cao, et al. "SWE-GPT: A Process-Centric Language Model for Automated Software Improvement." Proceedings of the ACM on Software Engineering 2, ISSTA (2025): 2362–83. https://doi.org/10.1145/3728981.

Full text

Abstract:

Large language models (LLMs) have demonstrated remarkable performance in code generation, significantly enhancing the coding efficiency of developers. Recent advancements in LLM-based agents have led to significant progress in end-to-end automatic software engineering (ASE), particularly in software maintenance (e.g., fixing software issues) and evolution (e.g., adding new features). Despite these encouraging advances, current research faces two major challenges. First, state-of-the-art performance primarily depends on closed-source models like GPT-4, which significantly limits the technology’

APA, Harvard, Vancouver, ISO, and other styles

45

Frodl, Andreas, Andreas Fuchs, Tayfun Yilmaz, Kaywan Izadpanah, Hagen Schmal, and Markus Siegel. "ChatGPT as a Source for Patient Information on Patellofemoral Surgery—A Comparative Study Amongst Laymen, Doctors, and Experts." Clinics and Practice 14, no. 6 (2024): 2376–84. http://dx.doi.org/10.3390/clinpract14060186.

Full text

Abstract:

Introduction: In November 2022, OpenAI launched ChatGPT for public use through a free online platform. ChatGPT is an artificial intelligence (AI) chatbot trained on a broad dataset encompassing a wide range of topics, including medical literature. The usability in the medical field and the quality of AI-generated responses are widely discussed and are the subject of current investigations. Patellofemoral pain is one of the most common conditions among young adults, often prompting patients to seek advice. This study examines the quality of ChatGPT as a source of information regarding patellofe

APA, Harvard, Vancouver, ISO, and other styles

46

Xu, Jie, Lu Lu, Xinwei Peng, et al. "Data Set and Benchmark (MedGPTEval) to Evaluate Responses From Large Language Models in Medicine: Evaluation Development and Validation." JMIR Medical Informatics 12 (June 28, 2024): e57674-e57674. http://dx.doi.org/10.2196/57674.

Full text

Abstract:

Abstract Background Large language models (LLMs) have achieved great progress in natural language processing tasks and demonstrated the potential for use in clinical applications. Despite their capabilities, LLMs in the medical domain are prone to generating hallucinations (not fully reliable responses). Hallucinations in LLMs’ responses create substantial risks, potentially threatening patients’ physical safety. Thus, to perceive and prevent this safety risk, it is essential to evaluate LLMs in the medical domain and build a systematic evaluation. Objective We developed a comprehensive evalua

APA, Harvard, Vancouver, ISO, and other styles

47

Kopitar, Leon, Iztok Fister, and Gregor Stiglic. "Using Generative AI to Improve the Performance and Interpretability of Rule-Based Diagnosis of Type 2 Diabetes Mellitus." Information 15, no. 3 (2024): 162. http://dx.doi.org/10.3390/info15030162.

Full text

Abstract:

Introduction: Type 2 diabetes mellitus is a major global health concern, but interpreting machine learning models for diagnosis remains challenging. This study investigates combining association rule mining with advanced natural language processing to improve both diagnostic accuracy and interpretability. This novel approach has not been explored before in using pretrained transformers for diabetes classification on tabular data. Methods: The study used the Pima Indians Diabetes dataset to investigate Type 2 diabetes mellitus. Python and Jupyter Notebook were employed for analysis, with the Ni

APA, Harvard, Vancouver, ISO, and other styles

48

Norsely, Febfi, Heidy Arviani, and Zainal Abidin Achmad. "Pengalaman Interaksi Pengguna Remaja Curhat dengan ChatGPT." Komunikologi: Jurnal Pengembangan Ilmu Komunikasi dan Sosial 7, no. 2 (2023): 120. http://dx.doi.org/10.30829/komunikologi.v7i2.16653.

Full text

Abstract:

<p><strong>Abstrak</strong></p><p>ChatGPT adalah sebuah kecerdasan buatan yang diluncurkan oleh OpenAI pada November 2022. Meskipun awalnya dirancang untuk menjawab pertanyaan-pertanyaan umum dan membantu dalam pekerjaan sehari-hari, pengguna mulai menggunakan ChatGPT sebagai tempat untuk curhat. Tujuan penelitian ini adalah untuk menyelidiki fakta, penyebab, dan konsekuensi dari fenomena penggunaan ChatGPT sebagai platform curhat bagi remaja. Pendekatan kualitatif digunakan dalam penelitian ini, dengan memanfaatkan studi fenomenologi Alfred Schutz. Data yang diku

APA, Harvard, Vancouver, ISO, and other styles

49

Thorlund, Kristian, Lucy Lloyd-Price, Reza Jafar, Milad Nourizade, Claire Burbridge, and Stacie Hudgens. "Screening oncology articles in a qualitative literature review using large language models: A comparison of GPT4 versus fine-tuned open source models using expert-annotated data." Journal of Clinical Oncology 42, no. 16_suppl (2024): e23196-e23196. http://dx.doi.org/10.1200/jco.2024.42.16_suppl.e23196.

Full text

Abstract:

e23196 Background: Clinical Outcome Assessment (COA) conceptual gap analyses for oncology are complex and time consuming. Artificial Intelligence may efficiently reduce time to completion of such analyses. We aimed to assess two AI models’ performance for literature screening to identify relevant qualitative oncology research. We also compared accuracy and run-time for both AI models. Methods: We manually curated a dataset of title/abstract screening (n = 1,700 study references) across 17 landscape reviews. Among these, 11 landscape reviews (n = 951 study references) spanning over were in onco

APA, Harvard, Vancouver, ISO, and other styles

50

Pavone, M., L. Palmieri, N. Bizzarri, et al. "Artificial Intelligence, the ChatGPT Large Language Model: Assessing the Accuracy of Responses to the Gynaecological Endoscopic Surgical Education and Assessment (GESEA) Level 1-2 knowledge tests." Facts, Views and Vision in ObGyn 16, no. 4 (2024): 449–56. https://doi.org/10.52054/fvvo.16.4.052.

Full text

Abstract:

Background: In 2022, OpenAI launched ChatGPT 3.5, which is now widely used in medical education, training, and research. Despite its valuable use for the generation of information, concerns persist about its authenticity and accuracy. Its undisclosed information source and outdated dataset pose risks of misinformation. Although it is widely used, AI-generated text inaccuracies raise doubts about its reliability. The ethical use of such technologies is crucial to uphold scientific accuracy in research. Objective: This study aimed to assess the accuracy of ChatGPT in doing GESEA tests 1 and 2. M

APA, Harvard, Vancouver, ISO, and other styles

We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!