Zobrazeno 1 - 10
of 286
pro vyhledávání: '"Kim, Juho"'
Autor:
Newman, Benjamin, Lee, Yoonjoo, Naik, Aakanksha, Siangliulue, Pao, Fok, Raymond, Kim, Juho, Weld, Daniel S., Chang, Joseph Chee, Lo, Kyle
When conducting literature reviews, scientists often create literature review tables - tables whose rows are publications and whose columns constitute a schema, a set of aspects used to compare and contrast the papers. Can we automatically generate t
Externí odkaz:
http://arxiv.org/abs/2410.22360
Autor:
Kim, Minsun, Kim, SeonGyeom, Lee, Suyoun, Yoon, Yoosang, Myung, Junho, Yoo, Haneul, Lim, Hyunseung, Han, Jieun, Kim, Yoonsu, Ahn, So-Yeon, Kim, Juho, Oh, Alice, Hong, Hwajung, Lee, Tak Yeon
This paper presents the development of a dashboard designed specifically for teachers in English as a Foreign Language (EFL) writing education. Leveraging LLMs, the dashboard facilitates the analysis of student interactions with an essay writing syst
Externí odkaz:
http://arxiv.org/abs/2410.15025
Autor:
Kim, Juho, Guerzhoy, Michael
A \textit{culture of honor} refers to a social system where individuals' status, reputation, and esteem play a central role in governing interpersonal relations. Past works have associated this concept with the United States (US) South and related wi
Externí odkaz:
http://arxiv.org/abs/2410.13887
Large language models (LLMs) can empower educators to build pedagogical conversational agents (PCAs) customized for their students. As students have different prior knowledge and motivation levels, educators must evaluate the adaptivity of their PCAs
Externí odkaz:
http://arxiv.org/abs/2410.04078
Autor:
Kim, Juho
Counterfactual regret minimization is a family of algorithms of no-regret learning dynamics capable of solving large-scale imperfect information games. We propose implementing this algorithm as a series of dense and sparse matrix and vector operation
Externí odkaz:
http://arxiv.org/abs/2408.14778
Creators are nothing without their audience, and thereby understanding their audience is the cornerstone of their professional achievement. Yet many creators feel lost while comprehending audiences with existing tools, which offer insufficient insigh
Externí odkaz:
http://arxiv.org/abs/2408.10937
Autor:
Kim, Hyunwoo, Choi, Yoonseo, Yang, Taehyun, Lee, Honggu, Park, Chaneon, Lee, Yongju, Kim, Jin Young, Kim, Juho
With large language models (LLMs), conversational search engines shift how users retrieve information from the web by enabling natural conversations to express their search intents over multiple turns. Users' natural conversation embodies rich but im
Externí odkaz:
http://arxiv.org/abs/2407.13166
Prevalent ungrammatical expressions and disfluencies in spontaneous speech from second language (L2) learners pose unique challenges to Automatic Speech Recognition (ASR) systems. However, few datasets are tailored to L2 learner speech. We publicly r
Externí odkaz:
http://arxiv.org/abs/2407.04280
Autor:
Kim, Minsun, Kim, SeonGyeom, Lee, Suyoun, Yoon, Yoosang, Myung, Junho, Yoo, Haneul, Lim, Hyunseung, Han, Jieun, Kim, Yoonsu, Ahn, So-Yeon, Kim, Juho, Oh, Alice, Hong, Hwajung, Lee, Tak Yeon
While ChatGPT has significantly impacted education by offering personalized resources for students, its integration into educational settings poses unprecedented risks, such as inaccuracies and biases in AI-generated content, plagiarism and over-reli
Externí odkaz:
http://arxiv.org/abs/2405.19691
AI intent alignment, ensuring that AI produces outcomes as intended by users, is a critical challenge in human-AI interaction. The emergence of generative AI, including LLMs, has intensified the significance of this problem, as interactions increasin
Externí odkaz:
http://arxiv.org/abs/2405.05678