# RECAST: Interactive Auditing of Automatic Toxicity Detection Models

arXiv: https://arxiv.org/abs/2001.01819 · HTML: https://mlsanity.com/paper/2001.01819/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jan 2020.

## Built on by (most cited first, 3 of 3)

- [Theories of "Gender" in NLP Bias Research](https://mlsanity.com/paper/2205.02526/) (2022)
- [Fairness and Bias in Multimodal AI: A Survey](https://mlsanity.com/paper/2406.19097/) (2024)
- [Thread With Caution: Proactively Helping Users Assess and Deescalate Tension in Their Online Discussions](https://mlsanity.com/paper/2212.01401/) (2022)

## Abstract (arXiv)

As toxic language becomes nearly pervasive online, there has been increasing interest in leveraging the advancements in natural language processing (NLP), from very large transformer models to automatically detecting and removing toxic comments. Despite the fairness concerns, lack of adversarial robustness, and limited prediction explainability for deep learning systems, there is currently little work for auditing these systems and understanding how they work for both developers and users. We present our ongoing work, RECAST, an interactive tool for examining toxicity detection models by visualizing explanations for predictions and providing alternative wordings for detected toxic speech.