Fairness for Unobserved Characteristics: Insights from Technological Impacts on Queer Communities

By Nenad Tomašev, Kevin R. McKee, Jackie Kay, Shakir Mohamed. 2021

109 citations recorded by the source corpus.

Advances in algorithmic fairness have largely omitted sexual orientation and gender identity. We explore queer concerns in privacy, censorship, language, online safety, health, and employment to study the positive and negative effects of artificial intelligence on queer communities. These issues underscore the need for new directions in fairness research that take into account a multiplicity of considerations, from privacy preservation, context sensitivity and process fairness, to an awareness of sociotechnical impact and the increasingly important role of inclusive and participatory research processes. Most current approaches for algorithmic fairness assume that the target characteristics for fairness---frequently, race and legal gender---can be observed or recorded. Sexual orientation and gender identity are prototypical instances of unobserved characteristics, which are frequently missing, unknown or fundamentally unmeasurable. This paper highlights the importance of developing new approaches for algorithmic fairness that break away from the prevailing assumption of observed characteristics.

Subfields: Safety Research, Sociology and Political Science, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Safety Research

In Sociology and Political Science

In Safety, Robustness & Interpretability

Citations in the corpus

Ethical and social risks of harm from Language Models (2021, background): “8 Disclosure of private information can have the same effects as doxing9, namely causing psychological and material harm (Douglas, 2016; LSEblog2017; Tomasev et al., 2021).”
Challenges in Detoxifying Language Models (2021, background): “We hope that future work can also consider a broader array of groups, including unobserved (Tomasev et al., 2021) and flexible (Andrus et al.”
PaLM 2 Technical Report (2023, methodology): “This rubric evolved from literature review on evaluation (Rauh et al., 2022; Dev et al., 2021b; Bowman & Dahl, 2021; Sambasivan et al., 2021; Paullada et al., 2021; Rodriguez et al., 2021; Schlangen, 2020; Denton et al., 2020; Selbst et al., 2019; Jacobs & Wallach, 2021; Tomasev et al., 2021; Welty ”
You reap what you sow: On the Challenges of Bias Evaluation Under Multilingual Settings (2022, background): “This is particularly problem-167 atic when building benchmarks for biases against com-168 munities that resist categorization based on observable characteristics (e.g. LGBTQIA+ and racialized people) and leads to reliance on existing stereotypes (Tomasev et al., 2021; Dev et al., 2021a).”
Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models (2022, background): “In practice, classiﬁcation of group membership is not well deﬁned because even a single facet of identity can be ﬂuid, composed of differing and competing factors, or unobserved or incorrectly reported in data [88, 99].”
Taxonomy of Risks posed by Language Models (2022, background): “Disclosure of private information can have the same effects as doxing (the publication of private or identifying information about an individual with malicious intent), causing psychological and material harm [51, 119, 181].”