Evaluating Short-Term Temporal Fluctuations of Social Biases in Social Media Data and Masked Language Models
This addresses concerns about amplifying biases in AI systems for users and developers, though it is incremental as it builds on existing bias detection research.
The study investigated how social biases in masked language models (MLMs) trained on social media data change over time, finding that most biases remain relatively stable despite exponential growth in data, with a few exceptions.
Social biases such as gender or racial biases have been reported in language models (LMs), including Masked Language Models (MLMs). Given that MLMs are continuously trained with increasing amounts of additional data collected over time, an important yet unanswered question is how the social biases encoded with MLMs vary over time. In particular, the number of social media users continues to grow at an exponential rate, and it is a valid concern for the MLMs trained specifically on social media data whether their social biases (if any) would also amplify over time. To empirically analyse this problem, we use a series of MLMs pretrained on chronologically ordered temporal snapshots of corpora. Our analysis reveals that, although social biases are present in all MLMs, most types of social bias remain relatively stable over time (with a few exceptions). To further understand the mechanisms that influence social biases in MLMs, we analyse the temporal corpora used to train the MLMs. Our findings show that some demographic groups, such as male, obtain higher preference over the other, such as female on the training corpora constantly.