• Korean Journal of Radiology
• /
• 제25권4호
• /
• pp.403-406
• /
• 2024

• 식물병연구
• /
• 제30권1호
• /
• pp.99-102
• /
• 2024

Integrated pest management is essential for controlling plant diseases that reduce crop yields. Rapid diagnosis is crucial for effective management in the event of an outbreak to identify the cause and minimize damage. Diagnosis methods range from indirect visual observation, which can be subjective and inaccurate, to machine learning and deep learning predictions that may suffer from biased data. Direct molecular-based methods, while accurate, are complex and time-consuming. However, the development of large multimodal models, like GPT-4, combines image recognition with natural language processing for more accurate diagnostic information. This study introduces GPT-4-based system for diagnosing plant diseases utilizing a detailed knowledge base with 1,420 host plants, 2,462 pathogens, and 37,467 pesticide instances from the official plant disease and pesticide registries of Korea. The AI plant doctor offers interactive advice on diagnosis, control methods, and pesticide use for diseases in Korea and is accessible at https://pdoc.scnu.ac.kr/.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 추계학술발표대회
• /
• pp.628-631
• /
• 2023

We present a new approach to evaluate the generated texts by Large Language Models (LLMs) for meme classification. Analyzing an image with embedded texts, i.e. meme, is challenging, even for existing state-of-the-art computer vision models. By leveraging large image-to-text models, we can extract image descriptions that can be used in other tasks, such as classification. In our methodology, we first generate image captions using BLIP-2 models. Using these captions, we use GPT-4 to evaluate the relationship between the caption and the meme text. The results show that OPT_6.7B provides a better rating than other LLMs, suggesting that the proposed method has a potential for meme classification.

• 국제학술발표논문집
• /
• The 10th International Conference on Construction Engineering and Project Management
• /
• pp.415-422
• /
• 2024

Recent advances in construction automation have led to increased use of deep learning-based computer vision technology for construction monitoring. However, monitoring systems based on supervised learning struggle with recognizing complex risk factors in construction environments, highlighting the need for adaptable solutions. Large multimodal models, pretrained on extensive image-text datasets, present a promising solution with their capability to recognize diverse objects and extract semantic information. This paper proposes a methodology that generates training data for multimodal models, including safety-centric descriptions using GPT-4V, and fine-tunes the LLaVA model using the LoRA method. Experimental results from seven construction site hazard scenarios show that the fine-tuned model accurately assesses safety status in images. These findings underscore the proposed approach's effectiveness in enhancing construction site safety monitoring and illustrate the potential of large multimodal models to tackle domain-specific challenges.

• 정보화정책
• /
• 제31권2호
• /
• pp.3-38
• /
• 2024

환각은 대형언어모형이나 대형 멀티모달 모형의 활용을 막는 큰 장벽이다. 본 연구에서는 최신 환각 연구 동향을 살펴보기 위해 챗 GPT 등장 이후인 2022년 12월부터 2024년 1월까지 아카이브(arXiv)에서 초록에 '환각'이 포함된 컴퓨터과학 분야 논문 654건을 수집해 빈도분석, 지식연결망 분석, 문헌 검토를 수행했다. 이를 통해 분야별 주요 저자, 주요 키워드, 주요 분야, 분야 간 관계를 분석했다. 분석 결과 '계산 및 언어'와 '인공지능', '컴퓨터비전 및 패턴인식', '기계학습' 분야의 연구가 활발했다. 이어 4개 주요 분야 연구 동향을 주요 저자를 중심으로 데이터 측면, 환각 탐지 측면, 환각 완화 측면으로 나눠 살펴보았다. 주요 연구 동향으로는 지도식 미세조정(SFT)과 인간 피드백 기반 강화학습(RLHF)을 통한 환각 완화, 생각의 체인(CoT) 등 추론 강화, 자동화와 인간 개입의 병행, 멀티모달 AI의 환각 완화에 대한 관심 증가 등을 들 수 있다. 본 연구는 환각 연구 최신 동향을 파악함으로써 공학계는 물론 인문사회계 후속 연구의 토대가 될 것으로 기대한다.