# Towards Conceptualization of "Fair Explanation": Disparate Impacts of anti-Asian Hate Speech Explanations on Content Moderators

arXiv: https://arxiv.org/abs/2310.15055 · HTML: https://mlsanity.com/paper/2310.15055/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 36 references that are in the map.
- First posted on arXiv 23 Oct 2023.

## Builds on (most cited first, 12 of 12)

- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models](https://mlsanity.com/paper/2101.00288/) (2021)
- [A Survey of the State of Explainable AI for Natural Language Processing](https://mlsanity.com/paper/2010.00711/) (2020)
- [Fairness in Machine Learning](https://mlsanity.com/paper/2012.15816/) (2020)
- [Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speech](https://mlsanity.com/paper/2302.07736/) (2023)
- [Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions](https://mlsanity.com/paper/2005.06676/) (2020)
- [Racism is a Virus: Anti-Asian Hate and Counterspeech in Social Media during the COVID-19 Crisis](https://mlsanity.com/paper/2005.12423/) (2020)
- [Issues with post-hoc counterfactual explanations: a discussion](https://mlsanity.com/paper/1906.04774/) (2019)
- [Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models](https://mlsanity.com/paper/2206.03945/) (2022)
- [But Who Protects the Moderators? The Case of Crowdsourced Image Moderation](https://mlsanity.com/paper/1804.10999/) (2018)
- ["If it didn't happen, why would I change my decision?": How Judges Respond to Counterfactual Explanations for the Public Safety Assessment](https://mlsanity.com/paper/2205.05424/) (2022)
- [The Impact of Explanations on Fairness in Human-AI Decision-Making: Protected vs Proxy Features](https://mlsanity.com/paper/2310.08617/) (2023)

## Built on by (most cited first, 6 of 6)

- [Explainability and Hate Speech: Structured Explanations Make Social Media Moderators Faster](https://mlsanity.com/paper/2406.04106/) (2024)
- [HateCOT: An Explanation-Enhanced Dataset for Generalizable Offensive Speech Detection via Large Language Models](https://mlsanity.com/paper/2403.11456/) (2024)
- [On the Risk of Evidence Pollution for Malicious Social Text Detection in the Era of LLMs](https://mlsanity.com/paper/2410.12600/) (2024)
- [CORTEX: Composite Overlay for Risk Tiering and Exposure in Operational AI Systems](https://mlsanity.com/paper/2508.19281/) (2025)
- [HateDebias: On the Diversity and Variability of Hate Speech Debiasing](https://mlsanity.com/paper/2406.04876/) (2024)
- [SMARTER: A Data-efficient Framework to Improve Toxicity Detection with Explanation via Self-augmenting Large Language Models](https://mlsanity.com/paper/2509.15174/) (2025)

## Abstract (arXiv)

Recent research at the intersection of AI explainability and fairness has focused on how explanations can improve human-plus-AI task performance as assessed by fairness measures. We propose to characterize what constitutes an explanation that is itself "fair" -- an explanation that does not adversely impact specific populations. We formulate a novel evaluation method of "fair explanations" using not just accuracy and label time, but also psychological impact of explanations on different user groups across many metrics (mental discomfort, stereotype activation, and perceived workload). We apply this method in the context of content moderation of potential hate speech, and its differential impact on Asian vs. non-Asian proxy moderators, across explanation approaches (saliency map and counterfactual explanation). We find that saliency maps generally perform better and show less evidence of disparate impact (group) and individual unfairness than counterfactual explanations. Content warning: This paper contains examples of hate speech and racially discriminatory language. The authors do not support such content. Please consider your risk of discomfort carefully before continuing reading!