mteb/multi-hatecheck

MultiHateClassification

An MTEB dataset

Massive Text Embedding Benchmark

Hate speech detection dataset with binary (hateful vs non-hateful) labels. Includes 25+ distinct types of hate and challenging non-hate, and 11 languages.

Task category	t2c
Domains	Constructed, Written
Reference	https://aclanthology.org/2022.woah-1.15/

How to evaluate on this task

You can evaluate an embedding model on this dataset using the following code:

import mteb

task = mteb.get_tasks(["MultiHateClassification"])
evaluator = mteb.MTEB(task)

model = mteb.get_model(YOUR_MODEL)
evaluator.run(model)

To learn more about how to run models on mteb task check out the GitHub repitory.

Citation

If you use this dataset, please cite the dataset as well as mteb, as this dataset likely includes additional processing as a part of the MMTEB Contribution.

@inproceedings{rottger-etal-2021-hatecheck,
  abstract = {Detecting online hate is a difficult task that even state-of-the-art models struggle with. Typically, hate speech detection models are evaluated by measuring their performance on held-out test data using metrics such as accuracy and F1 score. However, this approach makes it difficult to identify specific model weak points. It also risks overestimating generalisable model performance due to increasingly well-evidenced systematic gaps and biases in hate speech datasets. To enable more targeted diagnostic insights, we introduce HateCheck, a suite of functional tests for hate speech detection models. We specify 29 model functionalities motivated by a review of previous research and a series of interviews with civil society stakeholders. We craft test cases for each functionality and validate their quality through a structured annotation process. To illustrate HateCheck{'}s utility, we test near-state-of-the-art transformer models as well as two popular commercial models, revealing critical model weaknesses.},
  address = {Online},
  author = {R{\"o}ttger, Paul  and
Vidgen, Bertie  and
Nguyen, Dong  and
Waseem, Zeerak  and
Margetts, Helen  and
Pierrehumbert, Janet},
  booktitle = {Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},
  doi = {10.18653/v1/2021.acl-long.4},
  editor = {Zong, Chengqing  and
Xia, Fei  and
Li, Wenjie  and
Navigli, Roberto},
  month = aug,
  pages = {41--58},
  publisher = {Association for Computational Linguistics},
  title = {{H}ate{C}heck: Functional Tests for Hate Speech Detection Models},
  url = {https://aclanthology.org/2021.acl-long.4},
  year = {2021},
}

@inproceedings{rottger-etal-2022-multilingual,
  abstract = {Hate speech detection models are typically evaluated on held-out test sets. However, this risks painting an incomplete and potentially misleading picture of model performance because of increasingly well-documented systematic gaps and biases in hate speech datasets. To enable more targeted diagnostic insights, recent research has thus introduced functional tests for hate speech detection models. However, these tests currently only exist for English-language content, which means that they cannot support the development of more effective models in other languages spoken by billions across the world. To help address this issue, we introduce Multilingual HateCheck (MHC), a suite of functional tests for multilingual hate speech detection models. MHC covers 34 functionalities across ten languages, which is more languages than any other hate speech dataset. To illustrate MHC{'}s utility, we train and test a high-performing multilingual hate speech detection model, and reveal critical model weaknesses for monolingual and cross-lingual applications.},
  address = {Seattle, Washington (Hybrid)},
  author = {R{\"o}ttger, Paul  and
Seelawi, Haitham  and
Nozza, Debora  and
Talat, Zeerak  and
Vidgen, Bertie},
  booktitle = {Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH)},
  doi = {10.18653/v1/2022.woah-1.15},
  editor = {Narang, Kanika  and
Mostafazadeh Davani, Aida  and
Mathias, Lambert  and
Vidgen, Bertie  and
Talat, Zeerak},
  month = jul,
  pages = {154--169},
  publisher = {Association for Computational Linguistics},
  title = {Multilingual {H}ate{C}heck: Functional Tests for Multilingual Hate Speech Detection Models},
  url = {https://aclanthology.org/2022.woah-1.15},
  year = {2022},
}


@article{enevoldsen2025mmtebmassivemultilingualtext,
  title={MMTEB: Massive Multilingual Text Embedding Benchmark},
  author={Kenneth Enevoldsen and Isaac Chung and Imene Kerboua and Márton Kardos and Ashwin Mathur and David Stap and Jay Gala and Wissam Siblini and Dominik Krzemiński and Genta Indra Winata and Saba Sturua and Saiteja Utpala and Mathieu Ciancone and Marion Schaeffer and Gabriel Sequeira and Diganta Misra and Shreeya Dhakal and Jonathan Rystrøm and Roman Solomatin and Ömer Çağatan and Akash Kundu and Martin Bernstorff and Shitao Xiao and Akshita Sukhlecha and Bhavish Pahwa and Rafał Poświata and Kranthi Kiran GV and Shawon Ashraf and Daniel Auras and Björn Plüster and Jan Philipp Harries and Loïc Magne and Isabelle Mohr and Mariya Hendriksen and Dawei Zhu and Hippolyte Gisserot-Boukhlef and Tom Aarsen and Jan Kostkan and Konrad Wojtasik and Taemin Lee and Marek Šuppa and Crystina Zhang and Roberta Rocca and Mohammed Hamdy and Andrianos Michail and John Yang and Manuel Faysse and Aleksei Vatolin and Nandan Thakur and Manan Dey and Dipam Vasani and Pranjal Chitale and Simone Tedeschi and Nguyen Tai and Artem Snegirev and Michael Günther and Mengzhou Xia and Weijia Shi and Xing Han Lù and Jordan Clive and Gayatri Krishnakumar and Anna Maksimova and Silvan Wehrli and Maria Tikhonova and Henil Panchal and Aleksandr Abramov and Malte Ostendorff and Zheng Liu and Simon Clematide and Lester James Miranda and Alena Fenogenova and Guangyu Song and Ruqiya Bin Safi and Wen-Ding Li and Alessia Borghini and Federico Cassano and Hongjin Su and Jimmy Lin and Howard Yen and Lasse Hansen and Sara Hooker and Chenghao Xiao and Vaibhav Adlakha and Orion Weller and Siva Reddy and Niklas Muennighoff},
  publisher = {arXiv},
  journal={arXiv preprint arXiv:2502.13595},
  year={2025},
  url={https://arxiv.org/abs/2502.13595},
  doi = {10.48550/arXiv.2502.13595},
}

@article{muennighoff2022mteb,
  author = {Muennighoff, Niklas and Tazi, Nouamane and Magne, Lo{\"\i}c and Reimers, Nils},
  title = {MTEB: Massive Text Embedding Benchmark},
  publisher = {arXiv},
  journal={arXiv preprint arXiv:2210.07316},
  year = {2022}
  url = {https://arxiv.org/abs/2210.07316},
  doi = {10.48550/ARXIV.2210.07316},
}

Dataset Statistics

Dataset Statistics

The following code contains the descriptive statistics from the task. These can also be obtained using:

import mteb

task = mteb.get_task("MultiHateClassification")

desc_stats = task.metadata.descriptive_stats

{
    "test": {
        "num_samples": 11000,
        "number_of_characters": 502013,
        "number_texts_intersect_with_train": 16,
        "min_text_length": 1,
        "average_text_length": 45.63754545454545,
        "max_text_length": 135,
        "unique_text": 10990,
        "unique_labels": 2,
        "labels": {
            "0": {
                "count": 7661
            },
            "1": {
                "count": 3339
            }
        }
    },
    "train": {
        "num_samples": 11000,
        "number_of_characters": 505993,
        "number_texts_intersect_with_train": null,
        "min_text_length": 4,
        "average_text_length": 45.99936363636364,
        "max_text_length": 131,
        "unique_text": 10993,
        "unique_labels": 2,
        "labels": {
            "0": {
                "count": 7659
            },
            "1": {
                "count": 3341
            }
        }
    }
}

---

This dataset card was automatically generated using MTEB