AAVENUE: Detecting LLM Biases on NLU Tasks in AAVE via a Novel Benchmark

AAVENUE: Detecting LLM Biases on NLU Tasks in AAVE via a Novel Benchmark Abhay Gupta author Ece Yurtseven author Philip Meng author Kevin Zhu author 2024-11 text Proceedings of the Third Workshop on NLP for Positive Impact Daryna Dementieva editor Oana Ignat editor Zhijing Jin editor Rada Mihalcea editor Giorgio Piatti editor Joel Tetreault editor Steven Wilson editor Jieyu Zhao editor Association for Computational Linguistics Miami, Florida, USA conference publication gupta-etal-2024-aavenue 10.18653/v1/2024.nlp4pi-1.28 https://aclanthology.org/2024.nlp4pi-1.28/ 2024-11 327 333