Trustworthy Social Bias Measurement

12/20/2022
by   Rishi Bommasani, et al.
0

How do we design measures of social bias that we trust? While prior work has introduced several measures, no measure has gained widespread trust: instead, mounting evidence argues we should distrust these measures. In this work, we design bias measures that warrant trust based on the cross-disciplinary theory of measurement modeling. To combat the frequently fuzzy treatment of social bias in NLP, we explicitly define social bias, grounded in principles drawn from social science research. We operationalize our definition by proposing a general bias measurement framework DivDist, which we use to instantiate 5 concrete bias measures. To validate our measures, we propose a rigorous testing protocol with 8 testing criteria (e.g. predictive validity: do measures predict biases in US employment?). Through our testing, we demonstrate considerable evidence to trust our measures, showing they overcome conceptual, technical, and empirical deficiencies present in prior measures.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/07/2021

What do Bias Measures Measure?

Natural Language Processing (NLP) models propagate social biases about p...
research
07/06/2023

ValiTex – a unified validation framework for computational text-based measures of social science constructs

Guidance on how to validate computational text-based measures of social ...
research
10/18/2022

The Tail Wagging the Dog: Dataset Construction Biases of Social Bias Benchmarks

How reliably can we trust the scores obtained from social bias benchmark...
research
11/24/2022

Undesirable biases in NLP: Averting a crisis of measurement

As Natural Language Processing (NLP) technology rapidly develops and spr...
research
02/24/2023

In-Depth Look at Word Filling Societal Bias Measures

Many measures of societal bias in language models have been proposed in ...
research
01/28/2023

Comparing Intrinsic Gender Bias Evaluation Measures without using Human Annotated Examples

Numerous types of social biases have been identified in pre-trained lang...

Please sign up or login with your details

Forgot password? Click here to reset