Quantifying and alleviating political bias in language models

DOI10.1016/j.artint.2021.103654OpenAlexW4206590911MaRDI QIDQ2667847

Guangxuan Xu, Ruibo Liu, Jason Wei, Soroush Vosoughi, Chenyan Jia

Publication date: 2 March 2022

Published in: Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.artint.2021.103654

zbMATH Keywords

natural language generationbias in language modelsmeasuring biasmitigating biaspolitical bias

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Uses Software

• word2vec
• GloVe
• Tensor2Tensor
• BERT
• XLNet
• BERTScore
• Transformer-XL
• DialoGPT
• GPT-3
• mT5

Cites Work

• Necessary Stability Conditions for Neutral Type Systems With a Single Delay

This page was built for publication: Quantifying and alleviating political bias in language models