• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.301-305
• /
• 2023

최근 등장한 Large Language Models (LLM)은 자연어 처리 분야에서 눈에 띄는 성과를 보여주었지만, 주로 영어 중심의 연구로 진행되어 그 한계를 가지고 있다. 본 연구는 사전 학습된 LLM의 언어별 지식 전이 가능성을 한국어를 중심으로 탐구하였다. 이를 위해 한국어와 영어로 구성된 코드 스위칭 코퍼스를 구축하였으며, 기본 모델인 LLAMA-2와 코드 스위칭 코퍼스를 추가 학습한 모델 간의 성능 비교를 수행하였다. 결과적으로, 제안하는 방법론으로 학습한 모델은 두 언어 간의 희미론적 정보가 효과적으로 전이됐으며, 두 언어 간의 지식 정보 연계가 가능했다. 이 연구는 다양한 언어와 문화를 반영하는 다국어 LLM 연구와, 소수 언어를 포함한 AI 기술의 확산 및 민주화에 기여할 수 있을 것으로 기대된다.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.275-280
• /
• 2023

문서 그라운딩된 대화 시스템의 응답 성능 개선을 위한 방법론을 제안한다. 사전 학습된 거대 언어 모델 LLM(Large Language Model)인 Llama2 모델에 Zero-Shot In-Context learning을 적용하여 대화 마지막 유저 질문에 대한 응답을 생성하는 태스크를 수행하였다. 본 연구에서 제안한 응답 생성은 검색된 top-1 문서와 대화 기록을 참조해 초기 응답을 생성하고, 생성된 초기 응답을 기반으로 검색된 문서를 대상으로 재순위화를 수행한다. 이 후, 특정 순위의 상위 문서들을 이용해 최종 응답을 생성하는 과정으로 이루어진다. 검색된 상위 문서를 이용하는 응답 생성 방식을 Baseline으로 하여 본 연구에서 제안한 방식과 비교하였다. 그 결과, 본 연구에서 제안한 방식이 검색된 결과에 기반한 실험에서 Baseline 보다 F1, Bleu, Rouge, Meteor Score가 향상한 것을 확인 하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.371-372
• /
• 2023

본 논문에서는 대규모 언어 모델(Large Language Models)을 기반으로 한 입학 상담용 챗봇을 설계하였다. 입시 전문 LLM은 Polyglot-ko 5.8B을 베이스 모델로 대학의 입시 관련 데이터를 수집, 가공한 후 데이터 증강을 하여 파인튜닝 하였다. 또한, 모델 성능 향상을 위해 RLHF의 후 공정을 진행하였다. 제안 챗봇은 생성한 입시 LLM을 기반으로 웹브라우저를 통해 접근하여 입시 상담 자동 응답 서비스를 활용할 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.684-686
• /
• 2023

최근 대규모 언어모델 (large language models) 을 활용하여 다양한 자연어처리 문제를 추가학습 없이 풀어내기 위한 zero-shot 학습에 대한 연구가 활발히 수행되고 있다. 특히 프롬프트 튜닝(prompt tuning)을 활용하여 적은 학습만으로도 효과적으로 다양한 태스크에 적응하도록 돕는 방법이 최근 대규모 언어모델의 성능을 향상시키고 있다. 본 논문은 명령어 튜닝 (instruction tuning) 이 언어모델에 끼치는 영향을 분석하였다. 명령어 튜닝된 모델이 기존 언어모델과 비교하여 변화된 문장 생성 특징, 생성된 문장의 품질 등에 대한 분석을 수행하고 결과를 제시한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 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 KIEE Conference
• /
• 1995.07b
• /
• pp.634-636
• /
• 1995

This paper presents a new distance relay modeling techniques which avoids unnecessary computational procedure. A general-purpose simulation language, called MODELS, has been added to the software ATP(Alternative Transients Program) providing a new option to perform numerical and logical manipulations of variables of an electrical system. This language has been designed to replace the previous option TACS (Transient Analysis of Control Systems) which permits to simulate a control system in conjunction with a large power network. One purpose of this study is to build a structure for modeling of digital distance relays within EMTP MODELS. Contrary to the traditional methods, the new method using MODELS reduce the number of simulation steps in modeling the distance relay.

• Korean Journal of Radiology
• /
• v.25 no.1
• /
• pp.113-115
• /
• 2024

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.4
• /
• pp.29-35
• /
• 2020

In this paper, we propose a new structured entity recognition DeNERT model. Recently, the field of natural language processing has been actively researched using pre-trained language representation models with a large amount of corpus. In particular, the named entity recognition, which is one of the fields of natural language processing, uses a supervised learning method, which requires a large amount of training dataset and computation. Reinforcement learning is a method that learns through trial and error experience without initial data and is closer to the process of human learning than other machine learning methodologies and is not much applied to the field of natural language processing yet. It is often used in simulation environments such as Atari games and AlphaGo. BERT is a general-purpose language model developed by Google that is pre-trained on large corpus and computational quantities. Recently, it is a language model that shows high performance in the field of natural language processing research and shows high accuracy in many downstream tasks of natural language processing. In this paper, we propose a new named entity recognition DeNERT model using two deep learning models, DQN and BERT. The proposed model is trained by creating a learning environment of reinforcement learning model based on language expression which is the advantage of the general language model. The DeNERT model trained in this way is a faster inference time and higher performance model with a small amount of training dataset. Also, we validate the performance of our model's named entity recognition performance through experiments.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.1
• /
• pp.119-126
• /
• 2024

In building information model (BIM), it is difficult to train an artificial intelligence (AI) model due to the lack of sufficient data about individual projects in an architecture firm. In this paper, we present a methodology to correctly train an AI neural network model based on a large language model (LLM) to predict the steel structure product weight ratios in BIM. The proposed method, with the aid of the LLM, can overcome the inherent problem of limited data availability in BIM and handle a combination of natural language and numerical data. The experimental results showed that the proposed method demonstrated significantly higher accuracy than methods based on a smaller language model. The potential for effectively applying large language models in BIM is confirmed, leading to expectations of preventing building accidents and efficiently managing construction costs.

• Electronics and Telecommunications Trends
• /
• v.39 no.4
• /
• pp.82-92
• /
• 2024

This paper introduces the technological development trends in on-device SLMs (Small Language Models). Large Language Models (LLMs) based on the transformer model have gained global attention with the emergence of ChatGPT, providing detailed and sophisticated responses across various knowledge domains, thereby increasing their impact across society. While major global tech companies are continuously announcing new LLMs or enhancing their capabilities, the development of SLMs, which are lightweight versions of LLMs, is intensely progressing. SLMs have the advantage of being able to run as on-device AI on smartphones or edge devices with limited memory and computing resources, enabling their application in various fields from a commercialization perspective. This paper examines the technical features for developing SLMs, lightweight technologies, semiconductor technology development trends for on-device AI, and potential applications across various industries.