• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.443-447
• /
• 2023

검색 증강형 언어 모델은 입력과 연관된 문서들을 검색하고 텍스트 생성 과정에 통합하여 언어 모델의 생성 능력을 강화한다. 본 논문에서는 사전 학습된 대규모 언어 모델의 추가적인 학습 없이 In-Context 검색 증강으로 한국어 언어 모델의 생성 능력을 강화하고 기존 언어 모델 대비 성능이 증가함을 보인다. 특히 다양한 크기의 사전 학습된 언어 모델을 활용하여 검색 증강 결과를 보여 모든 규모의 사전 학습 모델에서 Perplexity가 크게 개선된 결과를 확인하였다. 또한 오픈 도메인 질의응답(Open-Domain Question Answering) 과업에서도 EM-19, F1-27.8 향상된 결과를 보여 In-Context 검색 증강형 언어 모델의 성능을 입증한다.

• Journal of Information Technology Services
• /
• v.10 no.4
• /
• pp.269-280
• /
• 2011

Mobile Augmented Reality (mobile AR), as one of the most prospective mobile applications, intends to provide richer experiences by annotating tags or virtual objects over the scene observed through camera embedded in a handheld device like smartphone or pad. In this paper, we analyzed the current status of the art of mobile AR and proposed a novel Points of Interest (POIs) data model based on ontology to provide context-aware information retrievals on lots of POIs data. Proposed ontology was expanded from the standard POIs data model of W3C POIs Working Group and established using OWL (Web Ontology Language) and Protege. We also proposed a context-aware mobile AR platform which can resolve three distinguished issues in current platforms : interoperability problem of POI tags, POIs data retrieval issue, and context-aware service issue.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.399-403
• /
• 2023

본 논문에서는 다중 문서 기반의 대화 시스템을 통한 효율적인 정보 검색과 응답 생성에 중점을 둡니다. 대규모 데이터 집합에서 정확한 문서를 선택하는 데 필요한 검색의 중요성을 강조하며, 현재 검색 방법의 한계와 문제점을 지적합니다. 또한 더 자연스러운 답변을 생성하기 위해 대규모 언어 모델을 사용하게 되면서 fine-tuning 시에 발생하는 제약과 낭비를 모델의 제로샷 생성 능력을 활용하여 개선하려는 방안을 제안하며, 모델의 크기와 자원의 효율성에 대한 고려사항을 논의합니다. 우리의 접근 방식은 대규모 언어 모델을 프롬프트와 함께 다중 문서로 학습 없이 정보를 검색하고 응답을 생성하는 방향으로 접근하여 대화 시스템의 효율성과 유용성을 향상시킬 수 있음을 제시합니다.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.690-693
• /
• 2023

언어 모델의 파라미터 수의 지속적인 증가로 100B 단위의 거대 언어모델 LLM(Large Language Model)을 구성 할 정도로 언어 모델의 크기는 증가 해 왔다. 이런 모델의 크기와 함께 성장한 다양한 Task의 작업 성능의 향상과 함께, 발전에는 환각(Hallucination) 및 윤리적 문제도 함께 떠오르고 있다. 이러한 문제 중 특히 환각 문제는 모델이 존재하지도 않는 정보를 실제 정보마냥 생성한다. 이러한 잘못된 정보 생성은 훌륭한 성능의 LLM에 신뢰성 문제를 야기한다. 환각 문제는 정보 검색을 통하여 입력 혹은 내부 표상을 증강하면 증상이 완화 되고 추가적으로 성능이 향상된다. 본 논문에서는 한국어 질의 응답에서 검색 증강을 통하여 모델의 개선점을 확인한다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.2
• /
• pp.87-92
• /
• 2024

In this paper, a RAG system was implemented using an existing Large Language Model (LLM) and Langchain library to develop a dental consultation chatbot. For this purpose, we collected contents from the webpage bulletin boards of domestic dental university hospitals and constructed consultation data with the advice and supervision of dental specialists. In order to divide the input consultation data into appropriate sizes, the chunk size and the size of the overlapping text in each chunk were set to 1001 and 100, respectively. As a result of the simulation, the Retrieval Augmented LLM searched for and output the consultation content that was most similar to the user input. It was confirmed that the accessibility of dental consultation and the accuracy of consultation content could be improved through the built chatbot.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.129-164
• /
• 2023

In a situation where the use and introduction of Large Language Models (LLMs) is expanding due to recent developments in generative AI technology, it is difficult to find actual application cases or implementation methods for the use of internal company data in existing studies. Accordingly, this study presents a method of implementing generative AI services using the LLM application architecture using the most widely used LangChain framework. To this end, we reviewed various ways to overcome the problem of lack of information, focusing on the use of LLM, and presented specific solutions. To this end, we analyze methods of fine-tuning or direct use of document information and look in detail at the main steps of information storage and retrieval methods using the retrieval augmented generation (RAG) model to solve these problems. In particular, similar context recommendation and Question-Answering (QA) systems were utilized as a method to store and search information in a vector store using the RAG model. In addition, the specific operation method, major implementation steps and cases, including implementation source and user interface were presented to enhance understanding of generative AI technology. This has meaning and value in enabling LLM to be actively utilized in implementing services within companies.

• International Journal of Computer Science & Network Security
• /
• v.22 no.6
• /
• pp.346-356
• /
• 2022

The jurisprudential legal rules govern the way Muslims react and interact to daily life. This creates a huge stream of questions, that require highly qualified and well-educated individuals, called Muftis. With Muslims representing almost 25% of the planet population, and the scarcity of qualified Muftis, this creates a demand supply problem calling for Automation solutions. This motivates the application of Artificial Intelligence (AI) to solve this problem, which requires a well-designed Question-Answering (QA) system to solve it. In this work, we propose a QA system, based on retrieval augmented generative transformer model for jurisprudential legal question. The main idea in the proposed architecture is the leverage of both state-of-the art transformer models, and the existing knowledge base of legal sources and question-answers. With the sensitivity of the domain in mind, due to its importance in Muslims daily lives, our design balances between exploitation of knowledge bases, and exploration provided by the generative transformer models. We collect a custom data set of 850,000 entries, that includes the question, answer, and category of the question. Our evaluation methodology is based on both quantitative and qualitative methods. We use metrics like BERTScore and METEOR to evaluate the precision and recall of the system. We also provide many qualitative results that show the quality of the generated answers, and how relevant they are to the asked questions.