CLMar 28, 2023

Towards Countering Essentialism through Social Bias Reasoning

AI2CMU
arXiv:2303.16173v15 citationsh-index: 49
Originality Incremental advance
AI Analysis

This work addresses social bias and stereotypes, which can lead to harm, but it is incremental as it builds on prior psychology and NLP research.

The paper tackled the problem of countering essentialist beliefs, such as 'liberals are stupid', by constructing five types of counterstatements and conducting human studies to evaluate their effectiveness, finding that broadening the scope of stereotypes was the most popular strategy.

Essentialist beliefs (i.e., believing that members of the same group are fundamentally alike) play a central role in social stereotypes and can lead to harm when left unchallenged. In our work, we conduct exploratory studies into the task of countering essentialist beliefs (e.g., ``liberals are stupid''). Drawing on prior work from psychology and NLP, we construct five types of counterstatements and conduct human studies on the effectiveness of these different strategies. Our studies also investigate the role in choosing a counterstatement of the level of explicitness with which an essentialist belief is conveyed. We find that statements that broaden the scope of a stereotype (e.g., to other groups, as in ``conservatives can also be stupid'') are the most popular countering strategy. We conclude with a discussion of challenges and open questions for future work in this area (e.g., improving factuality, studying community-specific variation) and we emphasize the importance of work at the intersection of NLP and psychology.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes