Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · tomh

toxigen_roberta

toxigen_roberta is a RoBERTa text-classification model from tomh. Its model card links it to ToxiGen for implicit hate-speech detection.

Publisher
tomh
Task
text-classification
Model type
roberta
License
Unknown
Library
transformers
Publication status
Accepted · not indexed

Model overview

toxigen_roberta is published by tomh as a text-classification model. The captured configuration identifies RobertaForSequenceClassification with model type roberta. According to the model card, it is associated with the ToxiGen dataset and paper for adversarial and implicit hate-speech detection.

Recorded capabilities

Implicit hate-speech detection

According to the model card, the model comes from the ToxiGen work and can be used to detect implicit hate speech.

Documented research lineage

According to the model card, the release is tied to the ToxiGen ACL 2022 paper by Hartvigsen, Gabriel, Palangi, Sap, Ray, and Kamar.

Transformers classification stack

Hub records list transformers and pytorch with endpoints compatibility for text-classification use.

Use cases in the source record

  • Implicit hate-speech detection workflows of the kind described in the ToxiGen model card.
  • Text-classification research that references the card's ToxiGen paper and dataset materials.

Limitations and unknowns

  • No license value was extracted from this record.
  • No parameter count was extracted from this record.
  • No context-window value was extracted from this record.
  • No evaluation results were extracted from this record.
  • Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: tomh/toxigen_roberta

Captured: Unknown. Processed: 2026-09-07T19:34:59.759586+00:00.

Thomas Hartvigsen, Saadia Gabriel, Hamid Palangi, Maarten Sap, Dipankar Ray, Ece Kamar. This model comes from the paper ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection and can be used to detect implicit hate speech. Please visit the Github Repository for the training dataset and further details. @inproceedings{hartvigsen2022toxigen, title = "{T}oxi{G}en: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection", author = "Hartvigsen, Thomas and Gabriel, Saadia and Palangi, Hamid and Sap, Maarten and Ray, Dipankar and Kamar, Ece", booktitle = "Proce…

F001F002F003F004F005F006F007F008F010F012