• Korean Journal of Cognitive Science
• /
• v.35 no.1
• /
• pp.23-48
• /
• 2024

Building human-aligned artificial intelligence (AI) for social support remains challenging despite the advancement of Large Language Models. We present a novel method, the Chain of Empathy (CoE) prompting, that utilizes insights from psychotherapy to induce LLMs to reason about human emotional states. This method is inspired by various psychotherapy approaches-Cognitive-Behavioral Therapy (CBT), Dialectical Behavior Therapy (DBT), Person-Centered Therapy (PCT), and Reality Therapy (RT)-each leading to different patterns of interpreting clients' mental states. LLMs without CoE reasoning generated predominantly exploratory responses. However, when LLMs used CoE reasoning, we found a more comprehensive range of empathic responses aligned with each psychotherapy model's different reasoning patterns. For empathic expression classification, the CBT-based CoE resulted in the most balanced classification of empathic expression labels and the text generation of empathic responses. However, regarding emotion reasoning, other approaches like DBT and PCT showed higher performance in emotion reaction classification. We further conducted qualitative analysis and alignment scoring of each prompt-generated output. The findings underscore the importance of understanding the emotional context and how it affects human-AI communication. Our research contributes to understanding how psychotherapy models can be incorporated into LLMs, facilitating the development of context-aware, safe, and empathically responsive AI.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2002.02a
• /
• pp.73-78
• /
• 2002

전기전도도 센서와 GPS장치를 연계하여 논 포장에서 실시간으로 전기전도도를 측정하는 기초시험을 실시하였다. 그 결과 아래와 같은 결과를 얻을 수 있었다. 가. 농기포장에서의 전기전도도의 평균값은 4.llmS/m인 반면, 같은 논 포장임에도 불구하고 호시포장에서는 평균값이 17.35mS/m를 나타내었다. 농기포장에서는 전기전도도의 변이계수가 34.66%, 호시포장에서는 13.15%로서 아주 큰 변이를 보였다. 나. 전기전도도 센서와 DGPS장치로부터 취득한 정보를 기반으로 지도를 작성할 수 있었다. Kriging 방법을 이용하여 지도를 작성함으로서 포장내·포장별 전기전도도 값의 공간변이가 존재함을 알 수 있었다. 다. 전기전도도 센서는 포장내·포장별 토양의 전기전도도를 측정하는데 문제점을 발견할 수 없었다. 그러나, 전기전도도 측정에 영향을 미치는 토양의 입자크기, 수분 함량 등의 영향을 고려한 좀 더 많은 연구가 진행되어야 할 것으로 판단되었다.

• Electronics and Telecommunications Trends
• /
• v.39 no.2
• /
• pp.54-65
• /
• 2024

This paper examines the trends of AI Foundation Model development and the competition to lead the related ecosystem, which have been rapidly unfolding since the emergence of ChatGPT, focusing on big tech companies in the United States. Based on this understanding of background knowledge, I analyzed and presented the main contents of the initial report reviewed by the UK competition authority, CMA, on potential competition issues that may arise in the process of innovations resulting from FM development. In addition, the trend and background of the CMA's investigation into the OpenAI-Microsoft partnership, whose importance has recently been highlighted, were also explained. It is expected that a reasonable domestic policy plan will be established by referring to these UK policy trends and monitoring & analyzing domestic industries.

• Electronics and Telecommunications Trends
• /
• v.39 no.1
• /
• pp.95-105
• /
• 2024

In natural language processing, large language models such as GPT-4 have recently been in the spotlight. The performance of natural language processing has advanced dramatically driven by an increase in the number of model parameters related to the number of acceptable input tokens and model size. Research on multimodal models that can simultaneously process natural language and image data is being actively conducted. Moreover, natural-language and image-based reasoning capabilities of large language models is being explored in robot artificial intelligence technology. We discuss research and related patent trends in robot task planning and code generation for robot control using large language models.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.86-90
• /
• 2023

최근 생성형 언어 모델이 주목받고 있으며, 이와 관련된 과제 또한 주목받고 있다. 언어 생성과 관련하여 많은 연구가 진행된 분야 중 하나가 '번역'이다. 번역과 관련하여, 최근 인공신경망 기반의 신경망 기계 번역(NMT)가 주로 연구되고 있으며, 뛰어난 성능을 보여주고 있다. 하지만 교착어인 한국어에서 언어유형학 상의 다른 분류에 속한 언어로 번역은 매끄럽게 번역되지 않는다는 한계가 여전하다. 따라서, 본 논문에서는 이러한 문제점을 극복하기 위해 한-영 사전을 통한 번역 품질 향상 방법을 제안한다. 또한 출력과 관련하여 소형 언어모델(sLLM)을 통해 CoT데이터셋을 구축하고 이를 기반으로 조정 학습하여 성능을 평가할 것이다.

• Journal of Microbiology
• /
• v.43 no.2
• /
• pp.158-165
• /
• 2005

Psilocybe fagicola comprises a complex of more than eight species, six of them in Mexico, and all of them possessing a long pseudorhiza, a characteristic not listed by Heim and Cailleux in 1959 in the original description of the type species, but described by Guzman in 1978 and 1983. The description of Psilocybe fagicola s.s. is here emended to include the length of the cheilocystidia of(6-) 12-20 (-30) llm, as well as the absence or scarcity of pleurocystidia. Psilocybe xalapensis and P. wassoniorum are considered to be synonymous with P. fagicola s.s. However, Psilocybe banderillensis and P. herrerae from Mexico, P. columbiana from Colombia, and P. keralensis from India are considered to be valid species within this complex. Moreover, P. novoxalapensis and P. teofilae, both from Mexico, are described as new species. Length of spores, presence or absence of pleurocystidia and their variations, and type of cheilocystidia constitute the principal defining characteristics of the species. Setaceous hyphae at the base of the stipe, as well as caulocystidia, lack taxonomic value, as do other morphological characteristics, including pileipellis and subpileipellis. A key to the eight considered species is also presented within the paper.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.3
• /
• pp.19-24
• /
• 2024

The future military combat environment is rapidly expanding the role and importance of artificial intelligence (AI) in defense, aligning with the current trends of declining military populations and evolving dynamics. Particularly, in the civilian sector, AI development has surged into new domains based on foundation models, such as OpenAI's Chat-GPT, categorized as Super-Giant AI or Hyperscale AI. The U.S. Department of Defense has organized Task Force Lima under the Chief Digital and AI Office (CDAO) to conduct research on the application of Large Language Models (LLM) and generative AI. Advanced military nations like China and Israel are also actively researching the integration of Super-Giant AI into their military capabilities. Consequently, there is a growing need for research within our military regarding the potential applications and fields of application for Super-Giant AI in weapon systems. In this paper, we compare the characteristics and pros and cons of specialized AI and Super-Giant AI (Foundation Models) and explore new application areas for Super-Giant AI in weapon systems. Anticipating future application areas and potential challenges, this research aims to provide insights into effectively integrating Super-Giant Artificial Intelligence into defense operations. It is expected to contribute to the development of military capabilities, policy formulation, and international security strategies in the era of advanced artificial intelligence.

• Journal of Arbitration Studies
• /
• v.25 no.3
• /
• pp.59-90
• /
• 2015

Since 1855, the federal courts of the United States have been empowered to assist in the gathering of evidence for use before foreign tribunals. Today, the source of that authority is 28 U.S.C. ${\S}1782$ which permits the courts to order a person "to give [ ] testimony... or to produce a document ... for use in a proceeding in a foreign or international tribunal${\cdots}$ ." It was generally assumed, until the United States Supreme Court's decision of Intel Corp. v. Advanced Micro Devices, Inc. in 2004, that arbitration tribunals were not "foreign tribunals" for purposes of 28 U.S.C. ${\S}1782$. While the issue in Intel did not involve an arbitration tribunal, a statement by the Supreme Court in dicta has called into question the exact parameters of the words "foreign tribunal," resulting in a split of opinion among the federal courts of the United States. This article explores the legislative history of 28 U.S.C. ${\S}1782$, examines the United States Supreme Court decision in Intel, and discusses the split among the courts of the United States regarding the interpretation of "foreign tribunal." The article further surveys emerging issues: is an arbitration tribunal in a case involving foreign parties and seated in the United States a "foreign tribunal"; does agreeing to the use of the IBA Rules on the Taking of Evidence in International Arbitration circumscribe the use of 28 U.S.C. ${\S}1782$; can a party be ordered to produce documents located outside the United States; and is there a role for judicial estoppel in determining whether an application pursuant to 28 U.S.C. ${\S}1782$ should be granted?

• The Journal of Korean Medicine
• /
• v.45 no.1
• /
• pp.203-214
• /
• 2024

Objectives: In the context of competency-based education emphasized in Korean Medicine, this study aimed to develop a pilot version of a CPX (Clinical Performance Examination) Practicing Chatbot utilizing large language models with prompt engineering. Methods: A standardized patient scenario was acquired from the National Institute of Korean Medicine and transformed into text format. Prompt engineering was then conducted using role prompting and few-shot prompting techniques. The GPT-4 API was employed, and a web application was created using the gradio package. An internal evaluation criterion was established for the quantitative assessment of the chatbot's performance. Results: The chatbot was implemented and evaluated based on the internal evaluation criterion. It demonstrated relatively high correctness and compliance. However, there is a need for improvement in confidentiality and naturalness. Conclusions: This study successfully piloted the CPX Practicing Chatbot, revealing the potential for developing educational models using AI technology in the field of Korean Medicine. Additionally, it identified limitations and provided insights for future developmental directions.

• Journal of Korean Society of Archives and Records Management
• /
• v.24 no.2
• /
• pp.65-88
• /
• 2024

This pilot study explores a method of extracting metadata values and descriptions from records using named entity recognition (NER), a technique in natural language processing (NLP), a subfield of artificial intelligence. The study focuses on handwritten records from the Guro Industrial Complex, produced during the 1960s and 1970s, comprising approximately 1,200 pages and 80,000 words. After the preprocessing process of the records, which included digitization, the study employed a publicly available language API based on Google's Bidirectional Encoder Representations from Transformers (BERT) language model to recognize entity names within the text. As a result, 173 names of people and 314 of organizations and institutions were extracted from the Guro Industrial Complex's past records. These extracted entities are expected to serve as direct search terms for accessing the contents of the records. Furthermore, the study identified challenges that arose when applying the theoretical methodology of NLP to real-world records consisting of semistructured text. It also presents potential solutions and implications to consider when addressing these issues.