Analyzing Stereotypes in Generative Text Inference Tasks

By Anna Sotnikova, Yang Trista Cao, Hal Daumé Iii, Rachel Rudinger. 2021

22 citations recorded by the source corpus.

Stereotypes are inferences drawn about people based on their demographic attributes, which may result in harms to users when a system is deployed. In generative language-inference tasks, given a premise, a model produces plausible hypotheses that follow either logically (natural language inference) or common-sensically (commonsense inference). Such tasks are therefore a fruitful setting in which to explore the degree to which NLP systems encode stereotypes. In our work, we study how stereotypes manifest when the potential targets of stereotypes are situated in real-life, neutral contexts. We collect human judgments on the presence of stereotypes in generated inferences, and compare how perceptions of stereotypes vary due to annotator positionality

Subfields: Artificial Intelligence, Literature and Literary Theory, Natural Language Processing, 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 Artificial Intelligence

In Literature and Literary Theory

In Natural Language Processing

In Safety, Robustness & Interpretability

Citations in the corpus

GLaM: Efficient Scaling of Language Models with Mixture-of-Experts (2021, background): “, 2020), as well as other social biases (Caliskan et al., 2017; Rudinger et al., 2017; Sap et al., 2020; Sotnikova et al., 2021).”
Theory-Grounded Measurement of U.S. Social Stereotypes in English Language Models (2022, methodology): “We manually construct the list by combining and picking groups from the list of social groups from Sotnikova et al. (2021) and Koch et al. (2016) and also adding social groups we think are stereotyped in U.S. culture.”