The Gaps between Pre-train and Downstream Settings in Bias Evaluation and Debiasing

16 January 2024

Papers citing "The Gaps between Pre-train and Downstream Settings in Bias Evaluation and Debiasing"

6 / 6 papers shown

Title
Evaluating Gender Bias of Pre-trained Language Models in Natural Language Inference by Considering All Labels Panatchakorn Anantaprayoon Masahiro Kaneko Naoaki Okazaki 64 16 0 18 Sep 2023
The Impact of Debiasing on the Performance of Language Models in Downstream Tasks is Underestimated Masahiro Kaneko Danushka Bollegala Naoaki Okazaki 42 5 0 16 Sep 2023
LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions Minghao Wu Abdul Waheed Chiyu Zhang Muhammad Abdul-Mageed Alham Fikri Aji ALM 135 119 0 27 Apr 2023
BBQ: A Hand-Built Bias Benchmark for Question Answering Alicia Parrish Angelica Chen Nikita Nangia Vishakh Padmakumar Jason Phang Jana Thompson Phu Mon Htut Sam Bowman 223 374 0 15 Oct 2021
Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP Timo Schick Sahana Udupa Hinrich Schütze 259 374 0 28 Feb 2021
Debiasing Pre-trained Contextualised Embeddings Masahiro Kaneko Danushka Bollegala 218 138 0 23 Jan 2021