HERB: Measuring Hierarchical Regional Bias in Pre-trained Language Models
This addresses regional discrimination in NLP, a global fairness issue, by introducing a novel evaluation metric, though it is incremental in extending bias analysis to hierarchical structures.
The paper tackles the problem of regional bias in pre-trained language models, which has been underexplored compared to other social biases, and finds that biases are influenced by geographical clustering, proposing a hierarchical evaluation method (HERB) that effectively quantifies and measures this bias across topics and downstream tasks.
Fairness has become a trending topic in natural language processing (NLP), which addresses biases targeting certain social groups such as genders and religions. However, regional bias in language models (LMs), a long-standing global discrimination problem, still remains unexplored. This paper bridges the gap by analysing the regional bias learned by the pre-trained language models that are broadly used in NLP tasks. In addition to verifying the existence of regional bias in LMs, we find that the biases on regional groups can be strongly influenced by the geographical clustering of the groups. We accordingly propose a HiErarchical Regional Bias evaluation method (HERB) utilising the information from the sub-region clusters to quantify the bias in pre-trained LMs. Experiments show that our hierarchical metric can effectively evaluate the regional bias with respect to comprehensive topics and measure the potential regional bias that can be propagated to downstream tasks. Our codes are available at https://github.com/Bernard-Yang/HERB.