Results 51 to 60 of about 34,912 (272)
Computational literature – creation under the auspices of AI and GPT models [PDF]
Dialogica: Revistă de Studii Culturale și Literatură, 2023 In this article is presented the impact of GPT natural language processing models and the evolution of AI on the computational literature. Analyzing the structuring and functioning of these neural networks based on observation, learning (pre-training ...
Rodica Gotca
doaj +1 more source
Memory-assisted prompt editing to improve GPT-3 after deployment
Conference on Empirical Methods in Natural Language Processing, 2022 Large LMs such as GPT -3 are powerful, but can commit mistakes that are obvious to humans. For example, GPT -3 would mistakenly interpret "What word is similar to good ?" to mean a homonym, while the user intended a synonym.
Aman Madaan +3 more
semanticscholar +1 more source
The AI Teacher Test: Measuring the Pedagogical Ability of Blender and GPT-3 in Educational Dialogues [PDF]
Educational Data Mining, 2022 How can we test whether state-of-the-art generative models, such as Blender and GPT-3, are good AI teachers, capable of replying to a student in an educational dialogue?
Anaïs Tack, C. Piech
semanticscholar +1 more source
GPT-3 Models are Few-Shot Financial Reasoners
Software Engineering Advances, 2023 Financial analysis is an important tool for evaluating company performance. Practitioners work to answer financial questions to make profitable investment decisions, and use advanced quantitative analyses to do so. As a result, Financial Question Answering (QA) is a question answering task that requires deep reasoning about numbers.
de Padua, Raul Salles +2 more
openaire +2 more sources
Putting GPT-3's Creativity to the (Alternative Uses) Test [PDF]
ICCC, 2022 AI large language models have (co-)produced amazing written works from newspaper articles to novels and poetry. These works meet the standards of the standard definition of creativity: being original and useful, and sometimes even the additional element ...
C. Stevenson +4 more
semanticscholar +1 more source
Feasibility of GPT-3 and GPT-4 for in-Depth Patient Education Prior to Interventional Radiological Procedures: A Comparative Analysis. [PDF]
Cardiovasc Intervent Radiol, 2023 This study explores the utility of the large language models, GPT-3 and GPT-4, for in-depth patient education prior to interventional radiology procedures. Further, differences in answer accuracy between the models were assessed. A total of 133 questions
Scheschenja M +5 more
europepmc +2 more sources
Herding AI Cats: Lessons from Designing a Chatbot by Prompting GPT-3
Conference on Designing Interactive Systems, 2023 Prompting Large Language Models (LLMs) is an exciting new approach to designing chatbots. But can it improve LLM’s user experience (UX) reliably enough to power chatbot products? Our attempt to design a robust chatbot by prompting GPT-3/4 alone suggests:
J.D. Zamfirescu-Pereira +7 more
semanticscholar +1 more source
Performance of ChatGPT, Bard, Claude, and Bing on the Peruvian National Licensing Medical Examination: a cross-sectional study [PDF]
Journal of Educational Evaluation for Health Professions, 2023 Purpose We aimed to describe the performance and evaluate the educational value of justifications provided by artificial intelligence chatbots, including GPT-3.5, GPT-4, Bard, Claude, and Bing, on the Peruvian National Medical Licensing Examination (P ...
Betzy Clariza Torres-Zegarra +10 more
doaj +1 more source
Systematic Evaluation of GPT-3 for Zero-Shot Personality Estimation [PDF]
Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, 2023 Very large language models (LLMs) perform extremely well on a spectrum of NLP tasks in a zero-shot setting. However, little is known about their performance on human-level NLP problems which rely on understanding psychological concepts, such as assessing
Adithya V Ganesan +3 more
semanticscholar +1 more source
Solving Math Word Problems concerning Systems of Equations with GPT-3
AAAI Conference on Artificial Intelligence, 2023 Researchers have been interested in developing AI tools to help students learn various mathematical subjects. One challenging set of tasks for school students is learning to solve math word problems.
Mingyu Zong, Bhaskar Krishnamachari
semanticscholar +1 more source