• The Mathematical Education
• /
• v.63 no.2
• /
• pp.187-207
• /
• 2024

In this study, we explored the feasibility of automatically scoring descriptive assessment items using GPT-4 based ChatGPT by comparing and analyzing the scoring results between teachers and GPT-4 based ChatGPT. For this purpose, three descriptive items from the permutation and combination unit for first-year high school students were selected from the KICE (Korea Institute for Curriculum and Evaluation) website. Items 1 and 2 had only one problem-solving strategy, while Item 3 had more than two strategies. Two teachers, each with over eight years of educational experience, graded answers from 204 students and compared these with the results from GPT-4 based ChatGPT. Various techniques such as Few-Shot-CoT, SC, structured, and Iteratively prompts were utilized to construct prompts for scoring, which were then inputted into GPT-4 based ChatGPT for scoring. The scoring results for Items 1 and 2 showed a strong correlation between the teachers' and GPT-4's scoring. For Item 3, which involved multiple problem-solving strategies, the student answers were first classified according to their strategies using prompts inputted into GPT-4 based ChatGPT. Following this classification, scoring prompts tailored to each type were applied and inputted into GPT-4 based ChatGPT for scoring, and these results also showed a strong correlation with the teachers' scoring. Through this, the potential for GPT-4 models utilizing prompt engineering to assist in teachers' scoring was confirmed, and the limitations of this study and directions for future research were presented.

• Journal of The Korean Association of Information Education
• /
• v.26 no.3
• /
• pp.197-207
• /
• 2022

In this paper, we develop a machine learning based block code generation and recommendation model for the purpose of reducing cognitive load of learners during coding education that learns the learner's block that has been made in the block programming environment using natural processing model and fine-tuning and then generates and recommends the selectable blocks for the next step. To develop the model, the training dataset was produced by pre-processing 50 block codes that were on the popular block programming language web site 'Entry'. Also, after dividing the pre-processed blocks into training dataset, verification dataset and test dataset, we developed a model that generates block codes based on LSTM, Seq2Seq, and GPT-2 model. In the results of the performance evaluation of the developed model, GPT-2 showed a higher performance than the LSTM and Seq2Seq model in the BLEU and ROUGE scores which measure sentence similarity. The data results generated through the GPT-2 model, show that the performance was relatively similar in the BLEU and ROUGE scores except for the case where the number of blocks was 1 or 17.

• Annual Conference of KIPS
• /
• 2024.05a
• /
• pp.830-833
• /
• 2024

As Large Language Models (LLM) like OpenAI's ChatGPT[1] continue to grow in popularity, new applications and services are expected to emerge. This paper introduces an experimental study on a smart web-builder application assistance system that combines Computer Vision with GUI object recognition and the ChatGPT (LLM). First of all, the research strategy employed computer vision technology in conjunction with Microsoft's "ChatGPT for Robotics: Design Principles and Model Abilities"[2] design strategy. Additionally, this research explores the capabilities of Large Language Model like ChatGPT in various application design tasks, specifically in assisting with web-builder tasks. The study examines the ability of ChatGPT to synthesize code through both directed prompts and free-form conversation strategies. The researchers also explored ChatGPT's ability to perform various tasks within the builder domain, including functions and closure loop inferences, basic logical and mathematical reasoning. Overall, this research proposes an efficient way to perform various application system tasks by combining natural language commands with computer vision technology and LLM (ChatGPT). This approach allows for user interaction through natural language commands while building applications.

• Proceedings of the Korean Society of Toxicology Conference
• /
• 2003.10b
• /
• pp.109-110
• /
• 2003

To validate a novel mouse model, gpt delta, for in vivo mutagenesis, the Mammalian Mutagenesis Society (MMS), a subgroup of the Environmental Mutagen Society of Japan (JEMS) (JEMS/MMS), performed a collaborative study as the third trial for transgenic animal assay. In this mouse model, point mutations and deletions re separately identified by gpt (6-thioguanine-resistant) and Spi- (sensitive to P2 interference) selections, respectively.(omitted)

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.19 no.1
• /
• pp.139-151
• /
• 2023

This study aims to gain insights into ChatGPT, which has recently received significant attention. The study utilized a mixed method involving case studies and news big data analysis. ChatGPT can be described as an optimized language model for dialogue. The question arises whether ChatGPT will replace Google search services, posing a potential threat to Google. It could hurt Google's advertising business, which is the foundation of its profits. With AI-based chatbots like ChatGPT likely to disrupt the web search industry, Google is establishing a new AI strategy. The study used the BIG KINDS service and analyzed 2,136 articles over six months, from August 23, 2022, to February 22, 2023. Thirty of these articles were written in 2022, while 2,106 have been reported recently as of February 22, 2023. Also, the study examined the contents of ChatGPT by utilizing literature research, news big data analysis, and use cases. Despite limitations such as the potential for false information, analyzing news big data and use cases suggests that ChatGPT is worth using.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.9
• /
• pp.69-77
• /
• 2024

This study evaluates the performance of second language acquisition models learning Korean and English using the GPT-2-Small model, analyzing the impact of various training conditions on performance. Four training conditions were used: monolingual learning, sequential learning, sequential-interleaved learning, and sequential-EWC learning. The model was trained using datasets from the National Institute of Korean Language and English from BabyLM Challenge, with performance measured through PPL and BLiMP metrics. Results showed that monolingual learning had the best performance with a PPL of 16.2 and BLiMP accuracy of 73.7%. In contrast, sequential-EWC learning had the highest PPL of 41.9 and the lowest BLiMP accuracy of 66.3%(p < 0.05). Monolingual learning proved most effective for optimizing model performance. The EWC regularization in sequential-EWC learning degraded performance by limiting weight updates, hindering new language learning. This research improves understanding of language modeling and contributes to cognitive similarity in AI language learning.

• International Journal of Advanced Culture Technology
• /
• v.12 no.2
• /
• pp.7-15
• /
• 2024

Despite a recent surge in multifaceted research on AI-integrated language learning, empirical studies in this area remain limited. This study adopts a Human-Generative AI parallel processing model to examine students' perceptions, asking 182 college students to independently construct knowledge and then compare their efforts with the results generated through in-classroom conversations with ChatGPT 3.5. In questionnaire responses, most students indicated that they found these activities useful and expressed a keen interest in learning various ways to utilize generative AI for language learning with instructor guidance. The findings confirm that ChatGPT's potential as a virtual conversation partner. Identifying specific reasons for the perceived usefulness of conversation activities and drawbacks of ChatGPT, this study emphasizes the importance of teachers staying informed about both the latest advances in technology and their limitations. We recommend that teachers endeavor to creatively design various classroom activities using AI technology.

• Therapeutic Science for Rehabilitation
• /
• v.13 no.1
• /
• pp.65-74
• /
• 2024

Objective : This study assessed ChatGPT, an artificial intelligence system based on a large language model, for its ability to pass the National Korean Occupational Therapy Licensure Examination (NKOTLE). Methods : Using NKOTLE questions from 2018 to 2022, provided by the Korea Health and Medical Personnel Examination Institute, this study employed English prompts to determine the accuracy of ChatGPT in providing correct answers. Two researchers independently conducted the entire process, and the average accuracy of both researchers was used to determine whether ChatGPT passed over the 5-year period. The degree of agreement between ChatGPT answers of the two researchers was assessed. Results : ChatGPT passed the 2020 examination but failed to pass the other 4 years' examination. Specifically, its accuracy in questions related to medical regulations ranged from 25% to 57%, whereas its accuracy in other questions exceeded 60%. ChatGPT exhibited a strong agreement between researchers, except for medical regulation questions, and this agreement was significantly correlated with accuracy. Conclusion : There are still limitations to the application of ChatGPT to answer questions influenced by language or culture. Future studies should explore its potential as an educational tool for students majoring in occupational therapy through optimized prompts and continuous learning from the data.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.3
• /
• pp.160-165
• /
• 2023

In this study, we propose an SNS sentence writing assistance system that utilizes YOLO and GPT to assist users in writing texts with images, such as SNS. We utilize the YOLO model to extract objects from images inserted during writing, and also extract meta-information such as GPS information and creation time information, and use them as prompt values for GPT. To use the YOLO model, we trained it on form image data, and the mAP score of the model is about 0.25 on average. GPT was trained on 1,000 blog text data with the topic of 'restaurant reviews', and the model trained in this study was used to generate sentences with two types of keywords extracted from the images. A survey was conducted to evaluate the practicality of the generated sentences, and a closed-ended survey was conducted to clearly analyze the survey results. There were three evaluation items for the questionnaire by providing the inserted image and keyword sentences. The results showed that the keywords in the images generated meaningful sentences. Through this study, we found that the accuracy of image-based sentence generation depends on the relationship between image keywords and GPT learning contents.

• The Mathematical Education
• /
• v.63 no.2
• /
• pp.139-163
• /
• 2024

The purpose of this study is to examine the capabilities of ChatGPT as a tool for supporting students in generating mathematical arguments that can be considered proofs. To examine this, we engaged students enrolled in a mathematics pathways course in evaluating and revising their original arguments using ChatGPT feedback. Students attempted to find and prove a method for the area of a triangle given its side lengths. Instead of directly asking students to prove a formula, we asked them to explore a method to find the area of a triangle given the lengths of its sides and justify why their methods work. Students completed these ChatGPT-embedded proving activities as class homework. To investigate the capabilities of ChatGPT as a proof tutor, we used these student homework responses as data for this study. We analyzed and compared original and revised arguments students constructed with and without ChatGPT assistance. We also analyzed student-written responses about their perspectives on mathematical proof and proving and their thoughts on using ChatGPT as a proof assistant. Our analysis shows that our participants' approaches to constructing, evaluating, and revising their arguments aligned with their perspectives on proof and proving. They saw ChatGPT's evaluations of their arguments as similar to how they usually evaluate arguments of themselves and others. Mostly, they agreed with ChatGPT's suggestions to make their original arguments more proof-like. They, therefore, revised their original arguments following ChatGPT's suggestions, focusing on improving clarity, providing additional justifications, and showing the generality of their arguments. Further investigation is needed to explore how ChatGPT can be effectively used as a tool in teaching and learning mathematical proof and proof-writing.