Social Bias

AbstractPretrained language models, especially masked language models (MLMs) have seen success across many NLP tasks. However, there is ample evidence that they use the cultural biases that are undoubtedly present …...

AbstractContextualized representations (e.g. ELMo, BERT) have become the default pretrained representations for downstream NLP applications. In some settings, this transition has rendered their static embedding predecessors (e.g. Word2Vec, GloVe) obsolete. …...

AbstractWarning: this paper contains content that may be offensive or upsetting. Language has the power to reinforce stereotypes and project social biases onto others. At the core of the challenge …...

AbstractEvaluation for many natural language understanding (NLU) tasks is broken: Unreliable and biased systems score so highly on standard benchmarks that there is little room for researchers who develop better …...

AbstractIt is well documented that NLP models learn social biases, but little work has been done on how these biases manifest in model outputs for applied tasks like question answering …...

AbstractAutomatic evaluation metrics are crucial to the development of generative systems. In recent years, pre-trained language model (PLM) based metrics, such as BERTScore, have been commonly adopted in various generation …...

AbstractWe study the relationship between task-agnostic intrinsic and task-specific extrinsic social bias evaluation measures for MLMs, and find that there exists only a weak correlation between these two types of …...

AbstractNatural language generation (NLG) models can propagate social bias towards particular demography. Though several studies investigated bias from data and model, NLG task distinctively uses stochastic decoder that can positively …...

AbstractLarge pre-trained language models are acknowledged to carry social bias towards different demographics, which can further amplify existing stereotypes in our society and cause even more harm. Text-to-SQL is an …...