---
title: "Multilingual and Explainable Text — Dementieva 2025"
description: "Online abusive language remains a problem despite regulation."
authors: ["Daryna Dementieva", "Nikolay Babakov", "Amit Ronen", "Abinew Ali Ayele", "Naquee Rizwan", "Florian Schneider", "Xintong Wang", "Seid Muhie Yimam", "Daniil Moskovskiy", "Elisei Stakovskii", "Eran Kaufman", "Ashraf Elnagar", "Animesh Mukherjee", "Alexander Panchenko"]
year: 2025
venue: "Proceedings of the 31st International Conference on Computational Linguistics"
source: "https://aclanthology.org/2025.coling-main.535/"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/papers/dementieva-2025-multilingual-explainable-text-detoxification-parallel/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/dementieva-2025-multilingual-explainable-text-detoxification-parallel/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2025](https://md.research.elamur.ai/free/papers/2025/page/2/) / Multilingual and Explainable Text Detoxification with Parallel Corpora

# Multilingual and Explainable Text Detoxification with Parallel Corpora

**Authors:** [Daryna Dementieva](https://md.research.elamur.ai/free/authors/daryna-dementieva/), Nikolay Babakov, Amit Ronen, [Abinew Ali Ayele](https://md.research.elamur.ai/free/authors/abinew-ali-ayele/), Naquee Rizwan, Florian Schneider, Xintong Wang, Seid Muhie Yimam, [Daniil Moskovskiy](https://md.research.elamur.ai/free/authors/daniil-moskovskiy/), Elisei Stakovskii, Eran Kaufman, Ashraf Elnagar et al. (14 authors) · **Year:** 2025 · **Venue:** Proceedings of the 31st International Conference on Computational Linguistics · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2025.coling-main.535/) · [PDF](https://aclanthology.org/2025.coling-main.535.pdf) · [OpenAlex](https://openalex.org/W4405470273)

**Citations:** 1 citations (openalex-snapshot · 2026-10-14) · [18](#cited-by) in our library, of the 140673 papers whose bibliographies we read

## Summary
Online abusive language remains a problem despite regulation. One remedy is text detoxification, which rewrites offensive text into a neutral version while keeping its meaning. The best systems rely on parallel toxic–neutral pairs, but such data existed for only a few mostly European languages. The authors manually built ParaDetox-style parallel corpora for German, Chinese, Arabic, Hindi and Amharic. Combined with existing English, Russian, Ukrainian and Spanish data, this gives nine languages. Toxicity was limited to vulgar or profane wording rather than deep insults or hate. Using LLMs as explainability tools, they analysed what characterises toxic and detoxified sentences in each language, which toxic collocations dominate, and which edits (such as deletion versus rephrasing) are needed. These insights fed a Chain-of-Thoughts prompting method for GPT-4 that adds information about detoxification clusters. Among the tested approaches, this method gave the strongest style-transfer accuracy and the best average joint score. The resources support detoxification research beyond high-resource European languages.

## Key points
- New parallel data per language (toxic candidates → detoxified pairs): German 3 521 → 1 103; Hindi 2 328 → 1 007; Amharic 2 995 → 1 000; Arabic 2 100 → 1 181; Chinese 1 380 → 1 000.
- German sources include GermEval 2018 and GermEval 2021 plus a hate-speech set by Ross et al. (2016); Hindi draws on HASOC (FIRE 2019). Annotation took about four months, with paid native-speaker annotators.
- Baselines included Delete, mBART-Large fine-tuned on human-curated versus translated data, and GPT-4 few-shot and CoT prompting. Delete was the best unsupervised method for Chinese, Arabic and Amharic.
- Human-curated fine-tuning data usually beat translated data, notably for German, Hindi, Ukrainian and Amharic, where cultural nuances matter.
- Data and code are on Hugging Face (textdetox) and GitHub, and they formed the basis of the TextDetox CLEF-2024 Shared Task.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Machine translation](https://md.research.elamur.ai/free/shelves/machine-translation/) · [Natural language processing](https://md.research.elamur.ai/free/shelves/nlp/)

## Cited by

Cited by

18 papers of our library cite it (of the 140673 whose bibliographies we read); 1 of them have a page here, 17 not yet.

- [Towards Safer Hebrew Communication: A Dataset for Offensive Language Detoxification](https://md.research.elamur.ai/free/papers/aclbulk-2025-vanetik-safer-hebrew-communication-dataset-offensive/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{dementieva2025multilingual,
  title = {{Multilingual and Explainable Text Detoxification with Parallel Corpora}},
  author = {Dementieva, Daryna and Babakov, Nikolay and Ronen, Amit and Ayele, Abinew Ali and Rizwan, Naquee and Schneider, Florian and Wang, Xintong and Yimam, Seid Muhie and Moskovskiy, Daniil and Stakovskii, Elisei and Kaufman, Eran and Elnagar, Ashraf and Mukherjee, Animesh and Panchenko, Alexander},
  booktitle = {Proceedings of the 31st International Conference on Computational Linguistics},
  year = {2025},
  url = {https://aclanthology.org/2025.coling-main.535/}
}
```

- [← previous MultiCoPIE: A Multilingual Corpus of Potentially Idiomatic Expressions for Cross-lingual PIE Disambiguation](https://md.research.elamur.ai/free/papers/sentsova-2025-multicopie-multilingual-corpus-potentially-idiomatic/)
- [next → Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention](https://md.research.elamur.ai/free/papers/yuan-2025-native-sparse-attention-hardware/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/papers/2025/page/2/)

## References

75 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Katherine Atwell, Sabit Hassan, and Malihe Alikhani. 2022. APPDIA: A discourse-aware transformer-based style transfer model for offensive social media conversations. In Proceedings of the 29th International Conference on Computational Linguistics, COLING 2022, Gyeongju, Republic of Korea, October 12-17, 2022, pages 6063–6074. International Committee on Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.2209.08207)
2. We explore the task of text detoxification with no intent to violate the freedom of speech, but rather Abinew Ali Ayele, Skadi Dinter, Tadesse Destaw Belay, to help mitigate digital violence, create safer on-Tesfa Tegegne Asfaw, Seid Muhie Yimam, and Chris Biemann. 2022. The 5Js in Ethiopia: Amharic hate line environments for children, and promote the speech data annotation using Toloka Crowdsourc-development of secure AI models. The ideal imple-ing Platform. In Proceedings of the 4th International mentation of detoxification models on communica-Conference on Information and Communication Tech-tion platforms would be as suggestions, rather than nology for Development for Africa (ICT4DA), pages 114–120, Bahir Dar, Ethiopia. forced corrections. A user-friendly interface for these suggestions should be considered by stake-Abinew Ali Ayele, Seid Muhie Yimam, Tadesse Destaw holders. [find](https://scholar.google.com/scholar?q=We+explore+the+task+of+text+detoxification+with+no+intent+to+violate+the+freedom+of+speech%2C+but+rather+Abinew+Ali+Ayele%2C+Skadi+Dinter%2C+Tadesse+Destaw+Belay%2C+to+help+mitigate+digital+violence%2C+create+s)
3. Belay, Tesfa Asfaw, and Chris Biemann. 2023. Ex-Additionally, detoxifying LLMs, not just human ploring Amharic hate speech data collection and clas-content, is a relevant topic. Already several ap-sification approaches. In Proceedings of the 14th 8007 International Conference on Recent Advances in Natural Language Processing, pages 49–59, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria. [find](https://scholar.google.com/scholar?q=Belay%2C+Tesfa+Asfaw%2C+and+Chris+Biemann%2E+2023%2E+Ex%2DAdditionally%2C+detoxifying+LLMs%2C+not+just+human+ploring+Amharic+hate+speech+data+collection+and+clas%2Dcontent%2C+is+a+relevant+topic%2E+Already+several+ap%2Dsif)
4. Wang. 2022. No language left behind: Scaling human-centered machine translation. CoRR, abs/2207.04672. [↗](https://arxiv.org/abs/2207.04672)
5. Anatoly Belchikov. 2019. Russian language toxic comments. [https://www.kaggle.com/blackmoon/russian-language-toxic-comments](https://www.kaggle.com/blackmoon/russian-language-toxic-comments). Accessed: 2023-12-14. [↗](https://www.kaggle.com/blackmoon/russian-language-toxic-comments)
6. Marta R. Costa-jussà, Mariano Coria Meglioli, Pierre Andrews, David Dale, Prangthip Hansanti, Elahe Kalbassi, Alexandre Mourachko, Christophe Ropers, and Carleigh Wood. 2024. Mutox: Universal multilingual audio-based toxicity dataset and zero-shot detector. CoRR, abs/2401.05060. [↗](https://arxiv.org/abs/2401.05060)
7. Kateryna Bobrovnyk. 2019a. Automated building and analysis of ukrainian twitter corpus for toxic text detection. In COLINS 2019. Volume II: Workshop. [find](https://scholar.google.com/scholar?q=Kateryna+Bobrovnyk%2E+2019a%2E+Automated+building+and+analysis+of+ukrainian+twitter+corpus+for+toxic+text+detection%2E+In+COLINS+2019%2E+Volume+II%3A+Workshop%2E)
8. Kateryna Bobrovnyk. 2019b. The dictionary of ukrainian obscene words. [https://github.com/saganoren/obscene-ukr](https://github.com/saganoren/obscene-ukr). Accessed: 2024-12-12. [↗](https://github.com/saganoren/obscene-ukr)
9. Aditya Bohra, Deepanshu Vijay, Vinay Singh, Syed Sarfaraz Akhtar, and Manish Shrivastava. 2018. A dataset of Hindi-English code-mixed social media text for hate speech detection. In Proceedings of the Second Workshop on Computational Modeling of People’s Opinions, Personality, and Emotions in Social Media, pages 36–41, New Orleans, Louisiana, USA. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Aditya+Bohra%2C+Deepanshu+Vijay%2C+Vinay+Singh%2C+Syed+Sarfaraz+Akhtar%2C+and+Manish+Shrivastava%2E+2018%2E+A+dataset+of+Hindi%2DEnglish+code%2Dmixed+social+media+text+for+hate+speech+detection%2E+In+Proceedings+of+the)
10. Eleftheria Briakou, Di Lu, Ke Zhang, and Joel Tetreault. 2021. Olá, bonjour, salve! XFORMAL: A benchmark for multilingual formality style transfer. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3199–3216, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Eleftheria+Briakou%2C+Di+Lu%2C+Ke+Zhang%2C+and+Joel+Tetreault%2E+2021%2E+Ol%C3%A1%2C+bonjour%2C+salve%21+XFORMAL%3A+A+benchmark+for+multilingual+formality+style+transfer%2E+In+Proceedings+of+the+2021+Conference+of+the+North+A)
11. Keith Carlson, Allen Riddell, and Daniel Rockmore. 2018. Evaluating prose style transfer with the bible. Royal Society open science, 5(10):171920. [↗](https://doi.org/10.1098/rsos.171920) [our card](https://md.research.elamur.ai/free/papers/carlson-2017-evaluating-prose-style-transfer-bible/)
12. Jennifer Cobbe. 2021. Algorithmic censorship by social platforms: Power and resistance. Philosophy & Technology, 34(4):739–766. [↗](https://doi.org/10.1007/s13347-020-00429-0)
13. Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. 2020. Unsupervised cross-lingual representation learning at scale. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, July 5-10, 2020, pages 8440–8451. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Alexis+Conneau%2C+Kartikay+Khandelwal%2C+Naman+Goyal%2C+Vishrav+Chaudhary%2C+Guillaume+Wenzek%2C+Francisco+Guzm%C3%A1n%2C+Edouard+Grave%2C+Myle+Ott%2C+Luke+Zettlemoyer%2C+and+Veselin+Stoyanov%2E+2020%2E+Unsupervised+cross%2Dlingu)
14. Marta R. Costa-jussà, James Cross, Onur Çelebi, Maha Elbayad, Kenneth Heafield, Kevin Heffernan, Elahe Kalbassi, Janice Lam, Daniel Licht, Jean Maillard, Anna Y. Sun, Skyler Wang, Guillaume Wenzek, Al Youngblood, Bapi Akula, Loïc Barrault, Gabriel Mejia Gonzalez, Prangthip Hansanti, John Hoffman, Semarley Jarrett, Kaushik Ram Sadagopan, Dirk Rowe, Shannon Spruit, Chau Tran, Pierre Andrews, Necip Fazil Ayan, Shruti Bhosale, Sergey Edunov, Angela Fan, Cynthia Gao, Vedanuj Goswami, Francisco Guzmán, Philipp Koehn, Alexandre Mourachko, Christophe Ropers, Safiyyah Saleem, Holger Schwenk, and Jeff David Dale, Anton Voronov, Daryna Dementieva, Varvara Logacheva, Olga Kozlova, Nikita Semenov, and Alexander Panchenko. 2021. Text detoxification using large pre-trained neural models. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 7979–7996, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Marta+R%2E+Costa%2Djuss%C3%A0%2C+James+Cross%2C+Onur+%C3%87elebi%2C+Maha+Elbayad%2C+Kenneth+Heafield%2C+Kevin+Heffernan%2C+Elahe+Kalbassi%2C+Janice+Lam%2C+Daniel+Licht%2C+Jean+Maillard%2C+Anna+Y%2E+Sun%2C+Skyler+Wang%2C+Guillaume+Wenzek%2C+Al)
15. Daryna Dementieva, Nikolay Babakov, and Alexander Panchenko. 2024a. MultiParaDetox: Extending text detoxification with parallel data to new languages. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers), pages 124–140, Mexico City, Mexico. Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.2404.02037)
16. Daryna Dementieva, Varvara Logacheva, Irina Nikishina, Alena Fenogenova, David Dale, I. Krotova, Nikita Semenov, Tatiana Shavrina, and Alexander Panchenko. 2022. RUSSE-2022: Findings of the First Russian Detoxification Shared Task Based on Parallel Corpora. COMPUTATIONAL LINGUIS-TICS AND INTELLECTUAL TECHNOLOGIES. [find](https://scholar.google.com/scholar?q=Daryna+Dementieva%2C+Varvara+Logacheva%2C+Irina+Nikishina%2C+Alena+Fenogenova%2C+David+Dale%2C+I%2E+Krotova%2C+Nikita+Semenov%2C+Tatiana+Shavrina%2C+and+Alexander+Panchenko%2E+2022%2E+RUSSE%2D2022%3A+Findings+of+the+First+Russ)
17. Daryna Dementieva, Daniil Moskovskiy, Nikolay Babakov, Abinew Ali Ayele, Naquee Rizwan, Fro-lian Schneider, Xintog Wang, Seid Muhie Yimam, Dmitry Ustalov, Elisei Stakovskii, Alisa Smirnova, Ashraf Elnagar, Animesh Mukherjee, and Alexander Panchenko. 2024b. Overview of the multilingual text detoxification task at pan 2024. In Working Notes of CLEF 2024 - Conference and Labs of the Evaluation Forum. CEUR-WS.org. [find](https://scholar.google.com/scholar?q=Daryna+Dementieva%2C+Daniil+Moskovskiy%2C+Nikolay+Babakov%2C+Abinew+Ali+Ayele%2C+Naquee+Rizwan%2C+Fro%2Dlian+Schneider%2C+Xintog+Wang%2C+Seid+Muhie+Yimam%2C+Dmitry+Ustalov%2C+Elisei+Stakovskii%2C+Alisa+Smirnova%2C+Ashraf+Eln)
18. Daryna Dementieva, Daniil Moskovskiy, David Dale, and Alexander Panchenko. 2023. Exploring methods for cross-lingual text style transfer: The case of text detoxification. In Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1083–1101, Nusa Dua, Bali. Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.2311.13937)
19. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171–4186, Minneapolis, Minnesota. Association for Computational Linguistics. City, Mexico. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Jacob+Devlin%2C+Ming%2DWei+Chang%2C+Kenton+Lee%2C+and+Kristina+Toutanova%2E+2019%2E+BERT%3A+Pre%2Dtraining+of+deep+bidirectional+transformers+for+language+understanding%2E+In+Proceedings+of+the+2019+Conference+of+the+N)
20. European Parliament and Council of the European Union. 2022. Regulation (eu) 2022/2065 of the european parliament and of the council of 19 october 2022 on a single market for digital services (digital services act) and amending directive 2000/31/ec. Official Journal of the European Union, L 277, 27.10.2022, p. 1–102. [find](https://scholar.google.com/scholar?q=European+Parliament+and+Council+of+the+European+Union%2E+2022%2E+Regulation+%28eu%29+2022%2F2065+of+the+european+parliament+and+of+the+council+of+19+october+2022+on+a+single+market+for+digital+services+%28digital)
21. Zachary Horvitz, Ajay Patel, Chris Callison-Burch, Zhou Yu, and Kathleen R. McKeown. 2024. Paraguide: Guided diffusion paraphrasers for plug-and-play textual style transfer. In Thirty-Eighth AAAI Conference on Artificial Intelligence, AAAI 2024, Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence, IAAI 2024, Fourteenth Symposium on Educational Advances in Artificial Intelligence, EAAI 2014, February 20-27, 2024, Vancouver, Canada, pages 18216–18224. AAAI Press. [find](https://scholar.google.com/scholar?q=Zachary+Horvitz%2C+Ajay+Patel%2C+Chris+Callison%2DBurch%2C+Zhou+Yu%2C+and+Kathleen+R%2E+McKeown%2E+2024%2E+Paraguide%3A+Guided+diffusion+paraphrasers+for+plug%2Dand%2Dplay+textual+style+transfer%2E+In+Thirty%2DEighth+AAAI+Conf)
22. Fangxiaoyu Feng, Yinfei Yang, Daniel Cer, Naveen Arivazhagan, and Wei Wang. 2022. Language-agnostic BERT sentence embedding. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2022, Dublin, Ireland, May 22-27, 2022, pages 878– 891. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Fangxiaoyu+Feng%2C+Yinfei+Yang%2C+Daniel+Cer%2C+Naveen+Arivazhagan%2C+and+Wei+Wang%2E+2022%2E+Language%2Dagnostic+BERT+sentence+embedding%2E+In+Proceedings+of+the+60th+Annual+Meeting+of+the+Association+for+Computatio) [our card](https://md.research.elamur.ai/free/papers/feng-2020-language-agnostic-bert-sentence-embedding/)
23. Griffin Floto, Mohammad Mahdi Abdollah Pour, Parsa Farinneya, Zhenwei Tang, Ali Pesaranghader, Manasa Bharadwaj, and Scott Sanner. 2023. DiffuDetox: A mixed diffusion model for text detoxification. In Findings of the Association for Computational Linguistics: ACL 2023, pages 7566–7574, Toronto, Canada. Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.2306.08505)
24. Robert James Gabriel. 2023. English full list of bad words and top swear words banned by google. [https://github.com/coffee-and-fun/google-profanity-words/blob/main/data/en.txt](https://github.com/coffee-and-fun/google-profanity-words/blob/main/data/en.txt). Accessed: 2024-12-12. [↗](https://github.com/coffee-and-fun/google-profanity-words/blob/main/data/en.txt)
25. Vaishali U. Gongane, Mousami V. Munot, and Alwin D. Anuse. 2024. A survey of explainable AI techniques for detection of fake news and hate speech on social media platforms. J. Comput. Soc. Sci., 7(1):587–623. [↗](https://doi.org/10.1007/s42001-024-00248-9)
26. Government of India. 2021. Information technology (intermediary guidelines and digital media ethics code) rules, 2021. Ministry of Electronics and Information Technology, Government of India. [find](https://scholar.google.com/scholar?q=Government+of+India%2E+2021%2E+Information+technology+%28intermediary+guidelines+and+digital+media+ethics+code%29+rules%2C+2021%2E+Ministry+of+Electronics+and+Information+Technology%2C+Government+of+India%2E)
27. Hatem Haddad, Hala Mulki, and Asma Oueslati. 2019. T-HSAB: A tunisian hate speech and abusive dataset. In Arabic Language Processing: From Theory to Practice - 7th International Conference, ICALP 2019, Nancy, France, October 16-17, 2019, Proceedings, volume 1108 of Communications in Computer and Information Science, pages 251–263. Springer. [find](https://scholar.google.com/scholar?q=Hatem+Haddad%2C+Hala+Mulki%2C+and+Asma+Oueslati%2E+2019%2E+T%2DHSAB%3A+A+tunisian+hate+speech+and+abusive+dataset%2E+In+Arabic+Language+Processing%3A+From+Theory+to+Practice+%2D+7th+International+Conference%2C+ICALP+2019)
28. Skyler Hallinan, Alisa Liu, Yejin Choi, and Maarten Sap. 2023. Detoxifying text with MaRCo: Controllable revision with experts and anti-experts. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 228–242, Toronto, Canada. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Skyler+Hallinan%2C+Alisa+Liu%2C+Yejin+Choi%2C+and+Maarten+Sap%2E+2023%2E+Detoxifying+text+with+MaRCo%3A+Controllable+revision+with+experts+and+anti%2Dexperts%2E+In+Proceedings+of+the+61st+Annual+Meeting+of+the+Associ)
29. Nhat Hoang, Xuan Long Do, Duc Anh Do, Duc Anh Vu, and Anh Tuan Luu. 2024. ToXCL: A unified framework for toxic speech detection and explanation. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 6460–6472, Mexico Joan L. Imbwaga, Nagaratna B. Chittaragi, and Shashidhar G. Koolagudi. 2024. Explainable hate speech detection using LIME. Int. J. Speech Technol., 27(3):793–815. [↗](https://doi.org/10.48550/arxiv.2403.16685)
30. Aiqi Jiang, Xiaohan Yang, Yang Liu, and Arkaitz Zubiaga. 2022. SWSR: A chinese dataset and lexicon for online sexism detection. Online Soc. Networks Media, 27:100182. [↗](https://doi.org/10.1016/j.osnem.2021.100182)
31. Jigsaw. 2017. Toxic comment classification challenge. [https://www.kaggle.com/c/jigsaw-toxic-comment-classification-challenge](https://www.kaggle.com/c/jigsaw-toxic-comment-classification-challenge). Accessed: 2024-03-18. [↗](https://www.kaggle.com/c/jigsaw-toxic-comment-classification-challenge)
32. Di Jin, Zhijing Jin, Zhiting Hu, Olga Vechtomova, and Rada Mihalcea. 2022. Deep learning for text style transfer: A survey. Computational Linguistics, 48(1):155–205. [↗](https://doi.org/10.1162/coli_a_00426)
33. Md Tawkat Islam Khondaker, Muhammad Abdul-Mageed, and Laks V. S. Lakshmanan. 2024. Greenl-lama: A framework for detoxification with explanations. CoRR, abs/2402.15951. [↗](https://arxiv.org/abs/2402.15951)
34. Enes Kulenović. 2023. Should democracies ban hate speech? hate speech laws and counterspeech. Ethical Theory and Moral Practice, 26(4):511–532. [↗](https://doi.org/10.1007/s10677-022-10336-2)
35. Teyun Kwon and Anandha Gopalan. 2021. CO-STAR: conceptualisation of stereotypes for analysis and reasoning. CoRR, abs/2112.00819. [↗](https://arxiv.org/abs/2112.00819)
36. Chak Tou Leong, Yi Cheng, Jiashuo Wang, Jian Wang, and Wenjie Li. 2023. Self-detoxifying language models via toxification reversal. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023, pages 4433–4449. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Chak+Tou+Leong%2C+Yi+Cheng%2C+Jiashuo+Wang%2C+Jian+Wang%2C+and+Wenjie+Li%2E+2023%2E+Self%2Ddetoxifying+language+models+via+toxification+reversal%2E+In+Proceedings+of+the+2023+Conference+on+Empirical+Methods+in+Natura)
37. Juncen Li, Robin Jia, He He, and Percy Liang. 2018. Delete, retrieve, generate: a simple approach to sentiment and style transfer. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2018, New Orleans, Louisiana, USA, June 1-6, 2018, Volume 1 (Long Papers), pages 1865–1874. Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.1804.06437) [our card](https://md.research.elamur.ai/free/papers/li-2018-delete-retrieve-generate-simple-approach/)
38. Yinhan Liu, Jiatao Gu, Naman Goyal, Xian Li, Sergey Edunov, Marjan Ghazvininejad, Mike Lewis, and Luke Zettlemoyer. 2020. Multilingual denoising pre-training for neural machine translation. Trans. Assoc. Comput. Linguistics, 8:726–742. [↗](https://doi.org/10.1162/tacl_a_00343)
39. Varvara Logacheva, Daryna Dementieva, Sergey Ustyantsev, Daniil Moskovskiy, David Dale, Irina Krotova, Nikita Semenov, and Alexander Panchenko. 2022. ParaDetox: Detoxification with parallel data. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6804–6818, Dublin, Ireland. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Varvara+Logacheva%2C+Daryna+Dementieva%2C+Sergey+Ustyantsev%2C+Daniil+Moskovskiy%2C+David+Dale%2C+Irina+Krotova%2C+Nikita+Semenov%2C+and+Alexander+Panchenko%2E+2022%2E+ParaDetox%3A+Detoxification+with+parallel+data%2E+In+P) [our card](https://md.research.elamur.ai/free/papers/logacheva-2022-paradetox-detoxification-parallel-data/)
40. Junyu Lu, Bo Xu, Xiaokun Zhang, Changrong Min, Liang Yang, and Hongfei Lin. 2023. Facilitating fine-grained detection of Chinese toxic language: Hierarchical taxonomy, resources, and benchmarks. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, pages 16235– 16250. [find](https://scholar.google.com/scholar?q=Junyu+Lu%2C+Bo+Xu%2C+Xiaokun+Zhang%2C+Changrong+Min%2C+Liang+Yang%2C+and+Hongfei+Lin%2E+2023%2E+Facilitating+fine%2Dgrained+detection+of+Chinese+toxic+language%3A+Hierarchical+taxonomy%2C+resources%2C+and+benchmarks%2E+In+Pr)
41. Scott M. Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, pages 4765–4774. [↗](https://doi.org/10.48550/arxiv.1705.07874) [our card](https://md.research.elamur.ai/free/papers/lundberg-2017-unified-approach-interpreting-model-predictions/)
42. Thomas Mandl, Sandip Modha, Prasenjit Majumder, Daksh Patel, Mohana Dave, Chintak Mandlia, and Aditya Patel. 2019. Overview of the hasoc track at fire 2019: Hate speech and offensive content identification in indo-european languages. In Proceedings of the 11th Annual Meeting of the Forum for Information Retrieval Evaluation, FIRE ’19, page 14–17, New York, NY, USA. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=Thomas+Mandl%2C+Sandip+Modha%2C+Prasenjit+Majumder%2C+Daksh+Patel%2C+Mohana+Dave%2C+Chintak+Mandlia%2C+and+Aditya+Patel%2E+2019%2E+Overview+of+the+hasoc+track+at+fire+2019%3A+Hate+speech+and+offensive+content+identific)
43. Binny Mathew, Punyajoy Saha, Seid Muhie Yimam, Chris Biemann, Pawan Goyal, and Animesh Mukherjee. 2021. Hatexplain: A benchmark dataset for explainable hate speech detection. In Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9, 2021, pages 14867–14875. AAAI Press. [find](https://scholar.google.com/scholar?q=Binny+Mathew%2C+Punyajoy+Saha%2C+Seid+Muhie+Yimam%2C+Chris+Biemann%2C+Pawan+Goyal%2C+and+Animesh+Mukherjee%2E+2021%2E+Hatexplain%3A+A+benchmark+dataset+for+explainable+hate+speech+detection%2E+In+Thirty%2DFifth+AAAI+Conf)
44. José María Molero, Jorge Pérez-Martín, Álvaro Rodrigo, and Anselmo Peñas. 2023. Offensive language detection in spanish social media: Testing from bag-of-words to transformers models. IEEE Access, 11:95639–95652. [↗](https://doi.org/10.1109/access.2023.3310244)
45. Edoardo Mosca, Daryna Dementieva, Tohid Ebrahim Ajdari, Maximilian Kummeth, Kirill Gringauz, Yutong Zhou, and Georg Groh. 2023. IFAN: An explainability-focused interaction framework for humans and NLP models. In Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: System Demonstrations, pages 59–76, Bali, Indonesia. Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.2303.03124)
46. Daniil Moskovskiy, Daryna Dementieva, and Alexander Panchenko. 2022. Exploring cross-lingual text detoxification with large multilingual language models. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, pages 346–354, Dublin, Ireland. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Daniil+Moskovskiy%2C+Daryna+Dementieva%2C+and+Alexander+Panchenko%2E+2022%2E+Exploring+cross%2Dlingual+text+detoxification+with+large+multilingual+language+models%2E+In+Proceedings+of+the+60th+Annual+Meeting+of+t)
47. Hamdy Mubarak, Kareem Darwish, Walid Magdy, Tamer Elsayed, and Hend Al-Khalifa. 2020. Overview of OSACT4 Arabic offensive language detection shared task. In Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection, pages 48–52, Marseille, France. European Language Resource Association. [find](https://scholar.google.com/scholar?q=Hamdy+Mubarak%2C+Kareem+Darwish%2C+Walid+Magdy%2C+Tamer+Elsayed%2C+and+Hend+Al%2DKhalifa%2E+2020%2E+Overview+of+OSACT4+Arabic+offensive+language+detection+shared+task%2E+In+Proceedings+of+the+4th+Workshop+on+Open%2DSou)
48. Niklas Muennighoff, Thomas Wang, Lintang Sutawika, Adam Roberts, Stella Biderman, Teven Le Scao, M. Saiful Bari, Sheng Shen, Zheng Xin Yong, Hailey Schoelkopf, Xiangru Tang, Dragomir Radev, Alham Fikri Aji, Khalid Almubarak, Samuel Albanie, Zaid Alyafeai, Albert Webson, Edward Raff, and Colin Raffel. 2023. Crosslingual generalization through multitask finetuning. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canada, July 9-14, 2023, pages 15991–16111. Association for Computational Linguistics. Sourabrata Mukherjee, Akanksha Bansal, Pritha Majumdar, Atul Kr. [↗](https://doi.org/10.48550/arxiv.2211.01786) [our card](https://md.research.elamur.ai/free/papers/muennighoff-2022-crosslingual-generalization-through-multitask-finetuning/)
49. Ojha, and Ondřej Dušek. 2023. Low-resource text style transfer for Bangla: Data & models. In Proceedings of the First Workshop on Bangla Language Processing (BLP-2023), pages 34–47, Singapore. Association for Computational Linguistics. Sourabrata Mukherjee, Atul Kr. [find](https://scholar.google.com/scholar?q=Ojha%2C+and+Ondr%CC%8Cej+Du%C5%A1ek%2E+2023%2E+Low%2Dresource+text+style+transfer+for+Bangla%3A+Data+%26+models%2E+In+Proceedings+of+the+First+Workshop+on+Bangla+Language+Processing+%28BLP%2D2023%29%2C+pages+34%E2%80%9347%2C+Singapore%2E+Associ)
50. Ojha, Akanksha Bansal, Deepak Alok, John P. McCrae, and Ondrej Dusek. 2024a. Multilingual text style transfer: Datasets & models for indian languages. CoRR, abs/2405.20805. Sourabrata Mukherjee, Atul Kr. [↗](https://arxiv.org/abs/2405.20805)
51. Ojha, and Ondrej Dusek. 2024b. Are large language models actually good at text style transfer? CoRR, abs/2406.05885. [↗](https://arxiv.org/abs/2406.05885)
52. Hala Mulki and Bilal Ghanem. 2021. Let-mi: An Arabic Levantine Twitter dataset for misogynistic language. In Proceedings of the Sixth Arabic Natural Language Processing Workshop, pages 154–163, Kyiv, Ukraine (Virtual). Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.2103.10195)
53. Hala Mulki, Hatem Haddad, Chedi Bechikh Ali, and Halima Alshabani. 2019. L-HSAB: A Levantine Twitter dataset for hate speech and abusive language. In Proceedings of the Third Workshop on Abusive Language Online, pages 111–118, Florence, Italy. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Hala+Mulki%2C+Hatem+Haddad%2C+Chedi+Bechikh+Ali%2C+and+Halima+Alshabani%2E+2019%2E+L%2DHSAB%3A+A+Levantine+Twitter+dataset+for+hate+speech+and+abusive+language%2E+In+Proceedings+of+the+Third+Workshop+on+Abusive+Langu)
54. Cicero Nogueira dos Santos, Igor Melnyk, and Inkit Padhi. 2018. Fighting offensive language on social media with unsupervised text style transfer. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 189–194, Melbourne, Australia. Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.1805.07685) [our card](https://md.research.elamur.ai/free/papers/santos-2018-fighting-offensive-language-social-media/)
55. OpenAI. 2022. Chatgpt: Optimizing language models for dialogue. Accessed: 2024-05-31. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2022%2E+Chatgpt%3A+Optimizing+language+models+for+dialogue%2E+Accessed%3A+2024%2D05%2D31%2E)
56. Juan Carlos Pereira-Kohatsu, Lara Quijano Sánchez, Federico Liberatore, and Miguel Camacho-Collados. 2019. Detecting and monitoring hate speech in twitter. Sensors, 19(21):4654. [↗](https://doi.org/10.3390/s19214654)
57. Juan Manuel Pérez, Damián Ariel Furman, Laura Alonso Alemany, and Franco M. Luque. 2022. RoBERTuito: a pre-trained language model for social media text in Spanish. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 7235–7243, Marseille, France. European Language Resources Association. [find](https://scholar.google.com/scholar?q=Juan+Manuel+P%C3%A9rez%2C+Dami%C3%A1n+Ariel+Furman%2C+Laura+Alonso+Alemany%2C+and+Franco+M%2E+Luque%2E+2022%2E+RoBERTuito%3A+a+pre%2Dtrained+language+model+for+social+media+text+in+Spanish%2E+In+Proceedings+of+the+Thirteenth+Lan)
58. Matt Post. 2018. A call for clarity in reporting BLEU scores. In Proceedings of the Third Conference on Machine Translation: Research Papers, WMT 2018, Belgium, Brussels, October 31 - November 1, 2018, pages 186–191. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Matt+Post%2E+2018%2E+A+call+for+clarity+in+reporting+BLEU+scores%2E+In+Proceedings+of+the+Third+Conference+on+Machine+Translation%3A+Research+Papers%2C+WMT+2018%2C+Belgium%2C+Brussels%2C+October+31+%2D+November+1%2C+2018) [our card](https://md.research.elamur.ai/free/papers/post-2018-call-clarity-reporting-bleu-scores/)
59. Shuofei Qiao, Yixin Ou, Ningyu Zhang, Xiang Chen, Yunzhi Yao, Shumin Deng, Chuanqi Tan, Fei Huang, and Huajun Chen. 2023. Reasoning with language model prompting: A survey. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5368–5393, Toronto, Canada. Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.2212.09597) [our card](https://md.research.elamur.ai/free/papers/qiao-2022-reasoning-language-model-prompting-survey/)
60. Sudha Rao and Joel Tetreault. 2018. Dear sir or madam, may I introduce the GYAFC dataset: Corpus, benchmarks and metrics for formality style transfer. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 129–140, New Orleans, Louisiana. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Sudha+Rao+and+Joel+Tetreault%2E+2018%2E+Dear+sir+or+madam%2C+may+I+introduce+the+GYAFC+dataset%3A+Corpus%2C+benchmarks+and+metrics+for+formality+style+transfer%2E+In+Proceedings+of+the+2018+Conference+of+the+Nort) [our card](https://md.research.elamur.ai/free/papers/rao-2018-dear-sir-or-madam-may/)
61. Marco Túlio Ribeiro, Sameer Singh, and Carlos Guestrin. 2016. "why should I trust you?": Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, August 13-17, 2016, pages 1135– 1144. ACM. [find](https://scholar.google.com/scholar?q=Marco+T%C3%BAlio+Ribeiro%2C+Sameer+Singh%2C+and+Carlos+Guestrin%2E+2016%2E+%22why+should+I+trust+you%3F%22%3A+Explaining+the+predictions+of+any+classifier%2E+In+Proceedings+of+the+22nd+ACM+SIGKDD+International+Conference+on) [our card](https://md.research.elamur.ai/free/papers/ribeiro-2016-why-should-i-trust-explaining/)
62. Julian Risch, Anke Stoll, Lena Wilms, and Michael Wiegand. 2021. Overview of the germeval 2021 shared task on the identification of toxic, engaging, and fact-claiming comments. In Proceedings of the GermEval 2021 Shared Task on the Identification of Toxic, Engaging, and Fact-Claiming Comments, GermEval@KONVENS 2021, Düsseldorf, Germany, September 6, 2021, pages 1–12. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Julian+Risch%2C+Anke+Stoll%2C+Lena+Wilms%2C+and+Michael+Wiegand%2E+2021%2E+Overview+of+the+germeval+2021+shared+task+on+the+identification+of+toxic%2C+engaging%2C+and+fact%2Dclaiming+comments%2E+In+Proceedings+of+the+G)
63. Björn Ross, Michael Rist, Guillermo Carbonell, Benjamin Cabrera, Nils Kurowsky, and Michael Wojatzki. 2016. Measuring the Reliability of Hate Speech Annotations: The Case of the European Refugee Crisis. In Proceedings of NLP4CMC III: 3rd Workshop on Natural Language Processing for Computer-Mediated Communication, volume 17 of Bochumer Linguistische Arbeitsberichte, pages 6–.9, Bochum, Germany. [find](https://scholar.google.com/scholar?q=Bj%C3%B6rn+Ross%2C+Michael+Rist%2C+Guillermo+Carbonell%2C+Benjamin+Cabrera%2C+Nils+Kurowsky%2C+and+Michael+Wojatzki%2E+2016%2E+Measuring+the+Reliability+of+Hate+Speech+Annotations%3A+The+Case+of+the+European+Refugee+Crisi)
64. Sarthak Roy, Ashish Harshvardhan, Animesh Mukherjee, and Punyajoy Saha. 2023. Probing LLMs for hate speech detection: strengths and vulnerabilities. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 6116–6128, Singapore. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Sarthak+Roy%2C+Ashish+Harshvardhan%2C+Animesh+Mukherjee%2C+and+Punyajoy+Saha%2E+2023%2E+Probing+LLMs+for+hate+speech+detection%3A+strengths+and+vulnerabilities%2E+In+Findings+of+the+Association+for+Computational+Li)
65. Aleksandr Semiletov. 2020. Toxic Russian Comments: Labelled comments from the popular Russian social network. [https://www.kaggle.com/alexandersemiletov/toxic-russian-comments](https://www.kaggle.com/alexandersemiletov/toxic-russian-comments). Accessed: 2023-12-14. [↗](https://www.kaggle.com/alexandersemiletov/toxic-russian-comments)
66. Zheyuan Ryan Shi, Claire Wang, and Fei Fang. 2020. Artificial intelligence for social good: A survey. CoRR, abs/2001.01818. [↗](https://arxiv.org/abs/2001.01818)
67. Inc Shutterstock. 2020. List of dirty, naughty, obscene, and otherwise bad words. [https://github.com/LDNOOBW/List-of-Dirty-Naughty-Obscene-and-Otherwise-Bad-Words](https://github.com/LDNOOBW/List-of-Dirty-Naughty-Obscene-and-Otherwise-Bad-Words). Accessed: 2024-12-12. [↗](https://github.com/LDNOOBW/List-of-Dirty-Naughty-Obscene-and-Otherwise-Bad-Words)
68. Chandan Singh, Jeevana Priya Inala, Michel Galley, Rich Caruana, and Jianfeng Gao. 2024. Rethinking interpretability in the era of large language models. CoRR, abs/2402.01761. [↗](https://arxiv.org/abs/2402.01761)
69. Yuqing Tang, Chau Tran, Xian Li, Peng-Jen Chen, Naman Goyal, Vishrav Chaudhary, Jiatao Gu, and Angela Fan. 2020. Multilingual translation with extensible multilingual pretraining and finetuning. CoRR, abs/2008.00401. [↗](https://arxiv.org/abs/2008.00401)
70. Mariona Taulé, Montserrat Nofre, Víctor Bargiela, and Xavier Bonet Casals. 2024. Newscom-tox: a corpus of comments on news articles annotated for toxicity in spanish. Lang. Resour. Evaluation, 58(4):1115– 1155. [↗](https://doi.org/10.1007/s10579-023-09711-x)
71. Rachel Ung. 2023. Formality Style Transfer between Japanese and English. Ph.D. thesis, Waseda University. [find](https://scholar.google.com/scholar?q=Rachel+Ung%2E+2023%2E+Formality+Style+Transfer+between+Japanese+and+English%2E+Ph%2ED%2E+thesis%2C+Waseda+University%2E)
72. Shang Wang, Tianqing Zhu, Bo Liu, Ming Ding, Xu Guo, Dayong Ye, Wanlei Zhou, and Philip S. Yu. 2024. Unique security and privacy threats of large language model: A comprehensive survey. CoRR, abs/2406.07973. [↗](https://arxiv.org/abs/2406.07973)
73. Michael Wiegand, Melanie Siegel, and Josef Ruppenhofer. 2018. Overview of the GermEval 2018 Shared Task on the Identification of Offensive Language. In Proceedings of GermEval 2018, 14th Conference on Natural Language Processing (KONVENS 2018), Vienna, Austria. [find](https://scholar.google.com/scholar?q=Michael+Wiegand%2C+Melanie+Siegel%2C+and+Josef+Ruppenhofer%2E+2018%2E+Overview+of+the+GermEval+2018+Shared+Task+on+the+Identification+of+Offensive+Language%2E+In+Proceedings+of+GermEval+2018%2C+14th+Conference+on)
74. Yifan Yao, Jinhao Duan, Kaidi Xu, Yuanfang Cai, Eric Sun, and Yue Zhang. 2023. A survey on large language model (LLM) security and privacy: The good, the bad, and the ugly. CoRR, abs/2312.02003. [↗](https://arxiv.org/abs/2312.02003) [our card](https://md.research.elamur.ai/free/papers/yao-2023-survey-large-language-model-llm/)
75. Chiyu Zhang, Honglong Cai, Yuezhang Li, Yuexin Wu, Le Hou, and Muhammad Abdul-Mageed. 2024. Distilling text style transfer with self-explanation from LLMs. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop), pages 200–211, Mexico City, Mexico. Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.2403.01106)