---
license: apache-2.0
language:
- en
---

# `infiniterik/desc-detoxify-sicon`

<!-- Provide a quick summary of what the model is/does. -->

Fine-tuned instance of [T5-Large](https://huggingface.co/t5-large) for detoxifying discourse surrounding abortion debate.
Implementation and ethical considerations are listed in the paper [Detoxifying Online Discourse: A Guided Response Generation Approach for Reducing Toxicity in User-Generated Text](https://github.com/infiniterik/detoxify/blob/main/pdfs/detoxify-paper.pdf).

Github repository can be found [here](https://www.github.com/infiniterik/detoxify).

## Citation

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

**BibTeX:**

```
@inproceedings{bose-etal-2023-detoxifying,
    title = "Detoxifying Online Discourse: A Guided Response Generation Approach for Reducing Toxicity in User-Generated Text",
    author = "Bose, Ritwik  and Perera, Ian  and Dorr, Bonnie",
    booktitle = "Proceedings of the First Workshop on Social Influence in Conversations (SICon 2023)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.sicon-1.2",
    pages = "9--14"
}
```