AI Chat AI Image Generator AI Video Text to Speech

Using Natural Sentences for Understanding Biases in Language Models

05/12/2022

∙

by Sarah Alnegheimish, et al.

∙

∙

Evaluation of biases in language models is often limited to synthetically generated datasets. This dependence traces back to the need for a prompt-style dataset to trigger specific behaviors of language models. In this paper, we address this gap by creating a prompt dataset with respect to occupations collected from real-world natural sentences present in Wikipedia. We aim to understand the differences between using template-based prompts and natural sentence prompts when studying gender-occupation biases in language models. We find bias evaluations are very sensitive to the design choices of template prompts, and we propose using natural sentence prompts for systematic evaluations to step away from design choices that could introduce bias in the observations.

Sarah Alnegheimish
5 publications
Alicia Guo
1 publication
Yi Sun
43 publications

page 1

page 2

page 3

page 4

research

∙ 04/12/2023

Measuring Gender Bias in West Slavic Language Models

Pre-trained language models have been known to perpetuate biases from th...

0 Sandra Martinková, et al. ∙

research

∙ 07/07/2023

Evaluating Biased Attitude Associations of Language Models in an Intersectional Context

Language models are trained on large-scale corpora that embed implicit b...

0 Shiva Omrani Sabbaghi, et al. ∙

research

∙ 04/12/2023

Measuring Normative and Descriptive Biases in Language Models Using Census Data

We investigate in this paper how distributions of occupations with respe...

0 Samia Touileb, et al. ∙

research

∙ 08/21/2023

FairBench: A Four-Stage Automatic Framework for Detecting Stereotypes and Biases in Large Language Models

Detecting stereotypes and biases in Large Language Models (LLMs) can enh...

0 Yanhong Bai, et al. ∙

research

∙ 06/12/2023

On the Amplification of Linguistic Bias through Unintentional Self-reinforcement Learning by Generative Language Models – A Perspective

Generative Language Models (GLMs) have the potential to significantly sh...

0 Minhyeok Lee, et al. ∙

research

∙ 09/30/2022

Exploiting Selection Bias on Underspecified Tasks in Large Language Models

In this paper we motivate the causal mechanisms behind sample selection ...

0 Emily McMilin, et al. ∙

research

∙ 09/16/2023

Investigating Subtler Biases in LLMs: Ageism, Beauty, Institutional, and Nationality Bias in Generative Models

LLMs are increasingly powerful and widely used to assist users in a vari...

0 Mahammed Kamruzzaman, et al. ∙