paper-with-me

홈 › Papers

On the Origins of Bias in NLP through the Lens of the Jim Code

2023-05-16 · Fatma Elsafoury, Gavin Abercrombie

In this paper, we trace the biases in current natural language processing (NLP) models back to their origins in racism, sexism, and homophobia over the last 500 years. We review literature from critical race theory, gender studies, data ethics, and digital humanities studies, and summarize the origins of bias in NLP models from these social science perspective. We show how the causes of the biases in the NLP pipeline are rooted in social issues. Finally, we argue that the only way to fix the bias and unfairness in NLP is by addressing the social problems that caused them in the first place and by incorporating social sciences and social scientists in efforts to mitigate bias in NLP models. We provide actionable recommendations for the NLP research community to do so.

📄 PDF Abstract BibTeX arXiv:2305.09281

Code (0)

등록된 구현이 없습니다.

Tasks

Ethics

Similar Papers 제목 키워드 기반

Exploring the Jungle of Bias: Political Bias Attribution in Language Models via Dependency Analysis

2023-11-15 · David F. Jenny, Yann Billeter, Mrinmaya Sachan, Bernhard Schölkopf 외

The rapid advancement of Large Language Models (LLMs) has sparked intense debate regarding the prevalence of bias in these models and its mitigation. Yet, as exemplified by both results on debiasing methods in the litera…

Decision MakingFairness

Language technology practitioners as language managers: arbitrating data bias and predictive bias in ASR

2022-02-25 · LREC 2022 6 · Nina Markl, Stephen Joseph McNulty

Despite the fact that variation is a fundamental characteristic of natural language, automatic speech recognition systems perform systematically worse on non-standardised and marginalised language varieties. In this pape…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

From Tables to Signals: Revealing Spectral Adaptivity in TabPFN

2025-11-23 · Jianqiao Zheng, Cameron Gordon, Yiping Ji, Hemanth Saratchandran 외 arxiv

Task-agnostic tabular foundation models such as TabPFN have achieved impressive performance on tabular learning tasks, yet the origins of their inductive biases remain poorly understood. In this work, we study TabPFN thr…

Image Denoising

Theoretical and Empirical Insights into the Origins of Degree Bias in Graph Neural Networks

2024-04-04 · Arjun Subramonian, Jian Kang, Yizhou Sun

Graph Neural Networks (GNNs) often perform better for high-degree nodes than low-degree nodes on node classification tasks. This degree bias can reinforce social marginalization by, e.g., privileging celebrities and othe…

Node Classification

Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview

2019-11-09 · ACL 2020 6 · Deven Shah, H. Andrew Schwartz, Dirk Hovy

An increasing number of works in natural language processing have addressed the effect of bias on the predicted outcomes, introducing mitigation techniques that act on different parts of the standard NLP pipeline (data a…

Selection bias