Linguistic Bias in ChatGPT: Language Models Reinforce Dialect
Discrimination

Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discrimination

13 June 2024

Papers citing "Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discrimination"

8 / 8 papers shown

Title
Sensing and Steering Stereotypes: Extracting and Applying Gender Representation Vectors in LLMs Hannah Cyberey Yangfeng Ji David Evans LLMSV 129 1 0 27 Feb 2025
Assessing Dialect Fairness and Robustness of Large Language Models in Reasoning Tasks Fangru Lin Shaoguang Mao Emanuele La Malfa Valentin Hofmann Adrian de Wynter Jing Yao Si-Qing Chen Michael Wooldridge J. Pierrehumbert Furu Wei 115 3 0 14 Oct 2024
Dialect prejudice predicts AI decisions about people's character, employability, and criminality Valentin Hofmann Pratyusha Kalluri Dan Jurafsky Sharese King 120 43 0 01 Mar 2024
Unintended Impacts of LLM Alignment on Global Representation Michael Joseph Ryan William B. Held Diyi Yang 97 42 0 22 Feb 2024
Evaluation of African American Language Bias in Natural Language Generation Nicholas Deas Jessica A. Grieser Shana Kleiner D. Patton Elsbeth Turcan Kathleen McKeown 43 29 0 23 May 2023
Prompting Multilingual Large Language Models to Generate Code-Mixed Texts: The Case of South East Asian Languages Zheng-Xin Yong Ruochen Zhang Jessica Zosa Forde Skyler Wang Arjun Subramonian ... Yinghua Tan Long Phan Rowena Garcia Thamar Solorio Alham Fikri Aji LRM 94 52 0 23 Mar 2023
Multi-VALUE: A Framework for Cross-Dialectal English NLP Caleb Ziems William B. Held Jingfeng Yang Jwala Dhamala Rahul Gupta Diyi Yang 81 44 0 15 Dec 2022
The State and Fate of Linguistic Diversity and Inclusion in the NLP World Pratik M. Joshi Sebastin Santy A. Budhiraja Kalika Bali Monojit Choudhury LMTD 115 850 0 20 Apr 2020

We use cookies and other tracking technologies to improve your browsing experience on our website, to show you personalized content and targeted ads, to analyze our website traffic, and to understand where our visitors are coming from. See our policy.