Výsledky vyhledávání - "Dong, Wenchao"

Report

Persona Setting Pitfall: Persistent Outgroup Biases in Large Language Models Arising from Social Identity Adoption

Autor: Dong, Wenchao, Zhunis, Assem, Jeong, Dongyoung, Chin, Hyojin, Han, Jiyoung, Cha, Meeyoung

Drawing parallels between human cognition and artificial intelligence, we explored how large language models (LLMs) internalize identities imposed by targeted prompts. Informed by Social Identity Theory, these identity assignments lead LLMs to distin

Externí odkaz: http://arxiv.org/abs/2409.03843

Zobrazit plný text záznamu

Report

I Am Not Them: Fluid Identities and Persistent Out-group Bias in Large Language Models

Autor: Dong, Wenchao, Zhunis, Assem, Chin, Hyojin, Han, Jiyoung, Cha, Meeyoung

We explored cultural biases-individualism vs. collectivism-in ChatGPT across three Western languages (i.e., English, German, and French) and three Eastern languages (i.e., Chinese, Japanese, and Korean). When ChatGPT adopted an individualistic person

Externí odkaz: http://arxiv.org/abs/2402.10436

Zobrazit plný text záznamu

Report

Global well-posedness for the 2D incompressible heat conducting Navier-Stokes equations with temperature-dependent coefficients and vacuum

Autor: Dong, Wenchao, Li, Qingyan

We consider the initial boundary problem of 2D non-homogeneous incompressible heat conducting Navier-Stokes equations with vacuum, where the viscosity and heat conductivity depend on temperature in a power law of Chapman-Enskog. We derive the global

Externí odkaz: http://arxiv.org/abs/2401.06433

Zobrazit plný text záznamu