# Empirical Analysis of Multi-Task Learning for Reducing Model Bias in Toxic Comment Detection

arXiv: https://arxiv.org/abs/1909.09758 · HTML: https://mlsanity.com/paper/1909.09758/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Sep 2019.

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

- [Challenges in Automated Debiasing for Toxic Language Detection](https://mlsanity.com/paper/2102.00086/) (2021)
- [Towards generalisable hate speech detection: a review on obstacles and solutions](https://mlsanity.com/paper/2102.08886/) (2021)
- [Theories of "Gender" in NLP Bias Research](https://mlsanity.com/paper/2205.02526/) (2022)
- [Toward Understanding Bias Correlations for Mitigation in NLP](https://mlsanity.com/paper/2205.12391/) (2022)
- [ID-XCB: Data-independent Debiasing for Fair and Accurate Transformer-based Cyberbullying Detection](https://mlsanity.com/paper/2402.16458/) (2024)
- [Determination of toxic comments and unintended model bias minimization using Deep learning approach](https://mlsanity.com/paper/2311.04789/) (2023)

## Abstract (arXiv)

With the recent rise of toxicity in online conversations on social media platforms, using modern machine learning algorithms for toxic comment detection has become a central focus of many online applications. Researchers and companies have developed a variety of models to identify toxicity in online conversations, reviews, or comments with mixed successes. However, many existing approaches have learned to incorrectly associate non-toxic comments that have certain trigger-words (e.g. gay, lesbian, black, muslim) as a potential source of toxicity. In this paper, we evaluate several state-of-the-art models with the specific focus of reducing model bias towards these commonly-attacked identity groups. We propose a multi-task learning model with an attention layer that jointly learns to predict the toxicity of a comment as well as the identities present in the comments in order to reduce this bias. We then compare our model to an array of shallow and deep-learning models using metrics designed especially to test for unintended model bias within these identity groups.