• Journal of the Korea Society of Computer and Information
• /
• v.28 no.8
• /
• pp.195-204
• /
• 2023

In this study, prompt engineering that improves prompts was explored to improve the performance of teaching and learning materials recommendations using generative artificial intelligence such as GPT and Stable Diffusion. Picture materials were used as the types of teaching and learning materials. To explore the impact of the prompt composition, a Zero-Shot prompt, a prompt containing learning target grade information, a prompt containing learning goals, and a prompt containing both learning target grades and learning goals were designed to collect responses. The collected responses were embedded using Sentence Transformers, dimensionalized to t-SNE, and visualized, and then the relationship between prompts and responses was explored. In addition, each response was clustered using the k-means clustering algorithm, then the adjacent value of the widest cluster was selected as a representative value, imaged using Stable Diffusion, and evaluated by 30 elementary school teachers according to the criteria for evaluating teaching and learning materials. Thirty teachers judged that three of the four picture materials recommended were of educational value, and two of them could be used for actual classes. The prompt that recommended the most valuable picture material appeared as a prompt containing both the target grade and the learning goal.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.4
• /
• pp.9-21
• /
• 2024

Deep learning has been developing rapidly in recent years, with many researchers working to utilize large language models in various domains. However, there are practical difficulties that developing and utilizing language models require massive data and high-performance computing resources. Therefore, in-context learning, which utilizes prompts to learn efficiently, has been introduced, but there needs to be clear criteria for effective prompts for learning. In this study, we propose a methodology for enhancing prompt-based learning performance by improving the PET technique, which is one of the contextual learning methods, to select PVPs that are similar to the context of existing data. To evaluate the performance of the proposed methodology, we conducted experiments with 30,100 restaurant review datasets collected from Yelp, an online business review platform. We found that the proposed methodology outperforms traditional PET in all aspects of accuracy, stability, and learning efficiency.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.47-52
• /
• 2022

환자와 주변인들에게 다양한 문제를 야기하는 치매와 조현병 진단을 위한 모델을 제안한다. 치매와 조현병 진단을 위해 프로토콜에 따라 녹음한 의사와 내담자 음성 시료를 전사 작업하여 분류 태스크를 수행하였다. 사전 학습한 언어 모델의 MLM Head를 이용해 분류 태스크를 수행하는 Prompt 기반의 분류 모델을 제안하였다. 또한 많은 수의 데이터 수를 확보하기 어려운 의료 분야에 효율적인 Few-Shot 학습 방식을 이용하였다. CLS 토큰을 미세조정하는 일반적 학습 방식의 Baseline과 비교해 Full-Shot 실험에서 7개 태스크 중 1개 태스크에서 macro, micro-F1 점수 모두 향상되었고, 3개 태스크에서 하나의 F1 점수만 향샹된 것을 확인 하였다. 반면, Few-Shot 실험에서는 7개 태스크 중 2개 태스크에서 macro, micro-F1 점수가 모두 향상되었고, 2개 태스크에서 하나의 F1 점수만 향상되었다.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.287-308
• /
• 2023

After launching its service in November 2022, ChatGPT has rapidly increased the number of users and is having a significant impact on all aspects of society, bringing a major turning point in the history of artificial intelligence. In particular, the inference ability of large language models such as ChatGPT is improving at a rapid pace through prompt engineering techniques. This reasoning ability can be considered as an important factor for companies that want to adopt artificial intelligence into their workflows or for individuals looking to utilize it. In this paper, we begin with an understanding of in-context learning that enables inference in large language models, explain the concept of prompt engineering, inference with in-context learning, and benchmark data. Moreover, we investigate the prompt engineering techniques that have rapidly improved the inference performance of large language models, and the relationship between the techniques.

• Nuclear Engineering and Technology
• /
• v.55 no.5
• /
• pp.1708-1717
• /
• 2023

The grade analysis of lead-zinc ore is the basis for the optimal development and utilization of deposits. In this study, a method combining Prompt Gamma Neutron Activation Analysis (PGNAA) technology and machine learning is proposed for lead-zinc mine borehole logging, which can identify lead-zinc ores of different grades and gangue in the formation, providing real-time grade information qualitatively and semi-quantitatively. Firstly, Monte Carlo simulation is used to obtain a gamma-ray spectrum data set for training and testing machine learning classification algorithms. These spectra are broadened, normalized and separated into inelastic scattering and capture spectra, and then used to fit different classifier models. When the comprehensive grade boundary of high- and low-grade ores is set to 5%, the evaluation metrics calculated by the 5-fold cross-validation show that the SVM (Support Vector Machine), KNN (K-Nearest Neighbor), GNB (Gaussian Naive Bayes) and RF (Random Forest) models can effectively distinguish lead-zinc ore from gangue. At the same time, the GNB model has achieved the optimal accuracy of 91.45% when identifying high- and low-grade ores, and the F₁ score for both types of ores is greater than 0.9.

• Korean Journal of Cognitive Science
• /
• v.14 no.3
• /
• pp.23-36
• /
• 2003

A comprehension-based approach to learning assumes that incoming information and background knowledge are integrated to form a mental representation which is subsequently used to incorporate new knowledge. It is demonstrated that this approach can be validated by comparing human and computational model performance in the prompt learning context. A computational model (ADAPT-UNIX) based on the construction-integration theory of comprehension (Kintsch, 1988; 1998) predicted how users learn from help prompts which are designed to assist UNIX composite command production. In addition, the comparison also revealed high similarity in composite production task performance between model and human. Educational implications of present research are discussed on the basis of the fact that prompt instructions have differential effect on learning and application as background knowledge varies.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.11
• /
• pp.481-492
• /
• 2023

This study explores how to build a Korean dataset to extract information from text using generative large language models. In modern society, mixed information circulates rapidly, and effectively categorizing and extracting it is crucial to the decision-making process. However, there is still a lack of Korean datasets for training. To overcome this, this study attempts to extract information using text-based zero-shot learning using a generative large language model to build a purposeful Korean dataset. In this study, the language model is instructed to output the desired result through prompt engineering in the form of "system"-"instruction"-"source input"-"output format", and the dataset is built by utilizing the in-context learning characteristics of the language model through input sentences. We validate our approach by comparing the generated dataset with the existing benchmark dataset, and achieve 25.47% higher performance compared to the KLUE-RoBERTa-large model for the relation information extraction task. The results of this study are expected to contribute to AI research by showing the feasibility of extracting knowledge elements from Korean text. Furthermore, this methodology can be utilized for various fields and purposes, and has potential for building various Korean datasets.

• Journal of Engineering Education Research
• /
• v.20 no.1
• /
• pp.53-62
• /
• 2017

This paper explored how university students viewed flipped learning from their own perspectives. Using qualitative research methods, 5 students from a Computer Graphics course at a mid-scale university in Seoul were interviewed for this purpose. Researchers collected data about their learning experiences, emotions, and reflections about flipped learning in general and its components such as online materials, in-class activities, and instructor guidance. Research findings indicated that students were not so much conscious about the unfamiliarity of the class, the increased work load, nor the online lectures. They rather prioritized 'what they could actually learn' from the course, and thus defined flipped learning as a method which enabled students to constantly check and fill in the gaps in their learning through team-based activities and prompt feedback from the professor. A combination of students' positive attitude and active participation in team-based activities, the overall atmosphere of the department which supported interactivity and collaboration, the professor's emphasis on learning-by-doing and student-centered learning appeared to form their notions of flipped learning. The use of technology did not appear to heavily impact students' conceptions of flipped learning. Researchers suggest that pedagogical beliefs of the professor, culture surrounding the learner, and the good match between the course content and instructional strategies are central for designing a successful flipped learning class.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.343-347
• /
• 2022

최근 자연어처리 분야에서는 BERT, RoBERTa, 그리고 BART와 같은 사전 학습된 언어 모델 (Pre-trained Language Models, PLM) 기반 미세 조정 학습을 통하여 여러 하위 과업에서 좋은 성능을 거두고 있다. 이는 사전 학습된 언어 모델 및 데이터 집합의 크기, 그리고 모델 구성의 중요성을 보여주며 대규모 사전 학습된 언어 모델이 각광받는 계기가 되었다. 하지만, 거대한 모델의 크기로 인하여 실제 산업에서 쉽게 쓰이기 힘들다는 단점이 명백히 존재함에 따라 최근 매개변수 효율적인 미세 조정 및 Few-Shot 학습 연구가 많은 주목을 받고 있다. 본 논문은 Prompt tuning, Prefix tuning와 프롬프트 기반 미세 조정 (Prompt-based fine-tuning)을 결합한 Few-Shot 학습 연구를 제안한다. 제안한 방법은 미세 조정 ←→ 사전 학습 간의 지식 격차를 줄일 뿐만 아니라 기존의 일반적인 미세 조정 기반 Few-Shot 학습 성능보다 크게 향상됨을 보인다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.5 no.3
• /
• pp.3-10
• /
• 1995

This paper proposedan on-line learning controller which can be applied to nonlinear systems. The proposed on-line learning controller is based on the universal approximation by the local affine mapping-based neural networks. It has self-organizing and learning capability to adapt itself to the new environment arising from the variation of operating point of the nonlinear system. Since the learning controller retains the knowledge of trained dynamics, it can promptly adapt itself to situations similar to the previously experienced one. This prompt adaptability of the proposed control system is illustrated through simulations.