# On the definition of toxicity in NLP

arXiv: https://arxiv.org/abs/2310.02357 · HTML: https://mlsanity.com/paper/2310.02357/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 25 references that are in the map.
- First posted on arXiv 3 Oct 2023.

## Builds on (most cited first, 6 of 6)

- [Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection](https://mlsanity.com/paper/2111.07997/) (2021)
- [Toxicity Detection: Does Context Really Matter?](https://mlsanity.com/paper/2006.00998/) (2020)
- [Is Your Toxicity My Toxicity? Exploring the Impact of Rater Identity on Toxicity Annotation](https://mlsanity.com/paper/2205.00501/) (2022)
- [Handling Bias in Toxic Speech Detection: A Survey](https://mlsanity.com/paper/2202.00126/) (2022)
- [Abuse is Contextual, What about NLP? The Role of Context in Abusive Language Annotation and Detection](https://mlsanity.com/paper/2103.14916/) (2021)
- [The Authors Matter: Understanding and Mitigating Implicit Bias in Deep Text Classification](https://mlsanity.com/paper/2105.02778/) (2021)

## Built on by (most cited first, 1 of 1)

- [Evading Toxicity Detection with ASCII-art: A Benchmark of Spatial Attacks on Moderation Systems](https://mlsanity.com/paper/2409.18708/) (2024)

## Abstract (arXiv)

The fundamental problem in toxicity detection task lies in the fact that the toxicity is ill-defined. This causes us to rely on subjective and vague data in models' training, which results in non-robust and non-accurate results: garbage in - garbage out. This work suggests a new, stress-level-based definition of toxicity designed to be objective and context-aware. On par with it, we also describe possible ways of applying this new definition to dataset creation and model training.