Výsledky vyhledávání

Report

Fakes of Varying Shades: How Warning Affects Human Perception and Engagement Regarding LLM Hallucinations

Autor: Nahar, Mahjabin, Seo, Haeseung, Lee, Eun-Ju, Xiong, Aiping, Lee, Dongwon

The widespread adoption and transformative effects of large language models (LLMs) have sparked concerns regarding their capacity to produce inaccurate and fictitious content, referred to as `hallucinations'. Given the potential risks associated with

Externí odkaz: http://arxiv.org/abs/2404.03745

Zobrazit plný text záznamu

Akademický článek

Frequent Mobile Electronic Medical Records Users Respond More Quickly to Emergency Department Consultation Requests: Retrospective Quantitative Study

Autor: Jung, Kwang Yul, Kim, SuJin, Kim, Kihyung, Lee, Eun Ju, Kim, Kyunga, Lee, Jeanhyoung, Choi, Jong Soo, Kang, Mira, Chang, Dong Kyung, Cha, Won Chul

Publikováno v: JMIR mHealth and uHealth, Vol 8, Iss 2, p e14487 (2020)

BackgroundSpecialty consultation is a critical aspect of emergency department (ED) practice, and a delay in providing consultation might have a significant clinical effect and worsen ED overcrowding. Although mobile electronic medical records (EMR) a

Externí odkaz: https://doaj.org/article/bc976c65081b4f37b6233bd48f24b2f6

Zobrazit plný text záznamu

Report

SQuARe: A Large-Scale Dataset of Sensitive Questions and Acceptable Responses Created Through Human-Machine Collaboration

Autor: Lee, Hwaran, Hong, Seokhee, Park, Joonsuk, Kim, Takyoung, Cha, Meeyoung, Choi, Yejin, Kim, Byoung Pil, Kim, Gunhee, Lee, Eun-Ju, Lim, Yong, Oh, Alice, Park, Sangchul, Ha, Jung-Woo

The potential social harms that large language models pose, such as generating offensive content and reinforcing biases, are steeply rising. Existing works focus on coping with this concern while interacting with ill-intentioned users, such as those

Externí odkaz: http://arxiv.org/abs/2305.17696

Zobrazit plný text záznamu