Transformer language models have received widespread public attention, yet their
generated text is often surprising even to NLP researchers. In this survey, we discuss over …

Using topic modeling and lexicon-based word similarity, we find that stories generated by
GPT-3 exhibit many known gender stereotypes. Generated stories depict different topics and …

Auditing NLP systems for computational harms like surfacing stereotypes is an elusive goal.
Several recent efforts have focused on benchmark datasets consisting of pairs of contrastive …

Knowledge-dependent tasks typically use two sources of knowledge: parametric, learned at
training time, and contextual, given as a passage at inference time. To understand how …

As the scope of machine learning broadens, we observe a recurring theme of algorithmic
monoculture: the same systems, or systems that share components (eg datasets, models) …

We present a general approach towards controllable societal biases in natural language
generation (NLG). Building upon the idea of adversarial triggers, we develop a method to …

Recent advancements in natural language processing (NLP) have catalyzed the
development of models capable of generating coherent and contextually relevant …

Recent studies show that Natural Language Processing (NLP) technologies propagate
societal biases about demographic groups associated with attributes such as gender, race …

We examine whether large language models (LLMs) exhibit race-and gender-based name
discrimination in hiring decisions, similar to classic findings in the social sciences (Bertrand …

Abstract Neural Machine Translation (NMT) systems exhibit problematic biases, such as
stereotypical gender bias in the translation of occupation terms into languages with …