Fairness in deep learning: A survey on vision and language research
Despite being responsible for state-of-the-art results in several computer vision and natural
language processing tasks, neural networks have faced harsh criticism due to some of their …
language processing tasks, neural networks have faced harsh criticism due to some of their …
Towards trustworthy and aligned machine learning: A data-centric survey with causality perspectives
The trustworthiness of machine learning has emerged as a critical topic in the field,
encompassing various applications and research areas such as robustness, security …
encompassing various applications and research areas such as robustness, security …
Robust Pronoun Fidelity with English LLMs: Are they Reasoning, Repeating, or Just Biased?
Robust, faithful, and harm-free pronoun use for individuals is an important goal for language
model development as their use increases, but prior work tends to study only one or two of …
model development as their use increases, but prior work tends to study only one or two of …
Debiasing methods for fairer neural models in vision and language research: A survey
Despite being responsible for state-of-the-art results in several computer vision and natural
language processing tasks, neural networks have faced harsh criticism due to some of their …
language processing tasks, neural networks have faced harsh criticism due to some of their …
Good, but not always fair: An evaluation of gender bias for three commercial machine translation systems
SA Piazzolla, B Savoldi, L Bentivogli - arXiv preprint arXiv:2306.05882, 2023 - arxiv.org
Machine Translation (MT) continues to make significant strides in quality and is increasingly
adopted on a larger scale. Consequently, analyses have been redirected to more nuanced …
adopted on a larger scale. Consequently, analyses have been redirected to more nuanced …
Evaluating Gender Bias in Machine Translation for Low-Resource Languages
While Machine Translation (MT) research has progressed over the years, translation
systems still suffer from exhibiting biases, including gender bias. While an active line of …
systems still suffer from exhibiting biases, including gender bias. While an active line of …
Step by Step to Fairness: Attributing Societal Bias in Task-oriented Dialogue Systems
Recent works have shown considerable improvements in task-oriented dialogue (TOD)
systems by utilizing pretrained large language models (LLMs) in an end-to-end manner …
systems by utilizing pretrained large language models (LLMs) in an end-to-end manner …
On Subjectivity, Bias and Fairness in Language Model Learning
Y Gaci - 2023 - theses.hal.science
With the staggering growth of language models in the last few years, language technology is
rapidly taking over some of the most influential procedures in modern society such as …
rapidly taking over some of the most influential procedures in modern society such as …