---
title: "A Position Paper on Toxic Reasoning: Grounding Categories of"
description: "Their alternative, called toxic reasoning, describes a message by what it asserts or implies. 22 references."
authors: ["Stefan F. Schouten", "Ilia Markov", "Piek Vossen"]
year: 2026
venue: "The Proceedings for the 15th Workshop on Computational Approaches to Subjectivity, Sentiment Social Media Analysis (WASSA 2026)"
source: "https://aclanthology.org/2026.wassa-1.12/"
doi: "10.18653/v1/2026.wassa-1.12"
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/en/papers/schouten-2026-position-paper-toxic-reasoning-grounding/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/schouten-2026-position-paper-toxic-reasoning-grounding/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/20/) / A Position Paper on Toxic Reasoning: Grounding Categories of Toxic Language in Implications and Attitudes

# A Position Paper on Toxic Reasoning: Grounding Categories of Toxic Language in Implications and Attitudes

**Authors:** Stefan F. Schouten, [Ilia Markov](https://md.research.elamur.ai/free/en/authors/ilia-markov/) and [Piek Vossen](https://md.research.elamur.ai/free/en/authors/piek-vossen/) · **Year:** 2026 · **Venue:** [The Proceedings for the 15th Workshop on Computational Approaches to Subjectivity, Sentiment Social Media Analysis (WASSA 2026)](https://md.research.elamur.ai/free/en/venues/wassa/) ([Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis 2026](https://md.research.elamur.ai/free/en/venues/wassa/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.wassa-1.12/) · [PDF](https://aclanthology.org/2026.wassa-1.12.pdf) · [DOI 10.18653/v1/2026.wassa-1.12](https://doi.org/10.18653/v1/2026.wassa-1.12) · [OpenAlex](https://openalex.org/W7140116074)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
This position paper examines how categories of toxic language (hate speech, abuse, offensive content) are defined in detection research, focusing on implicit toxicity and explainability. The authors survey existing definitions and find that they rely on four kinds of factors: the author's motivation (CAUSE), the impact on readers (EFFECT), surface wording (FORM), and conveyed content (MEANING). They argue that CAUSE- and EFFECT-based categories require world modelling and theory of mind, which makes them hard to operationalize, poorly explainable, and more subjective. They also show that toxic span annotation breaks down when toxicity is implied rather than stated. Their alternative, called toxic reasoning, describes a message by what it asserts or implies. Each implication is split into a core proposition and the attitudes of relevant stakeholders toward it, such as belief or preference held by the author, a typical person, or experts. To show that the schema works, they map the classes of existing taxonomies, the Implicit Hate Corpus and EDOS, onto it. The paper reports no experiments. Its contribution is a framework for more rigorous, explainable, and less subjective category definitions.

## Key points
- **Four defining factors.** The authors identify CAUSE, EFFECT, FORM and MEANING in existing definitions, illustrated with Perspective API categories:
  - "toxicity" is effect-based;
  - "profanity" is form-based;
  - "threat" is meaning-based.
- **Four concerns.** They raise objections to current definitions:
  - dependency on other loosely defined terms;
  - doubtful feasibility, since even LLMs may lack world models and theory of mind;
  - failure to truly explain predictions;
  - added subjectivity on top of the subjectivity of interpreting meaning.
- **Schema building blocks.** The schema uses content predicates such as NegativeSituation, Inferior, PositiveQuality and NegativeQuality (with NotHuman and Vermin as subtypes). It combines these with stakeholder attitudes such as belief and preference.
- **Mapping to existing datasets.** IHC classes are mapped onto the schema:
  - White Grievance;
  - Inferiority;
  - Incitement, extended to cover desired harm without author intent;
  - Stereotypes & Misinformation, framed as a lack of expert belief.
  
  EDOS is also mapped. Categories like "mansplaining" still inherently depend on CAUSE.
- **Future work.** The authors propose annotating datasets with schema traits. These traits could be used as prediction targets, auxiliary training objectives, or probing data.

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

## Institutions

- [Vrije Universiteit Amsterdam](https://md.research.elamur.ai/free/en/universities/vrije-universiteit-amsterdam/) — University, Amsterdam, Netherlands · 42 works · 3,372 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [💭 Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/) · 1,552 works · [💭 Social Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/social-psychology/) · 306 works

🧭 Topics (2): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,426 works · [🛡️ Bias, fairness & safety](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) · 517 works

## Cite

Cite as: Stefan F. Schouten, Ilia Markov and Piek Vossen. 2026. A Position Paper on Toxic Reasoning: Grounding Categories of Toxic Language in Implications and Attitudes. The Proceedings for the 15th Workshop on Computational Approaches to Subjectivity, Sentiment Social Media Analysis (WASSA 2026).

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

```bibtex
@inproceedings{schouten2026position,
  title = {{A Position Paper on Toxic Reasoning: Grounding Categories of Toxic Language in Implications and Attitudes}},
  author = {Stefan F. Schouten, Ilia Markov and Piek Vossen},
  booktitle = {The Proceedings for the 15th Workshop on Computational Approaches to Subjectivity, Sentiment Social Media Analysis (WASSA 2026)},
  year = {2026},
  doi = {10.18653/v1/2026.wassa-1.12},
  url = {https://doi.org/10.18653/v1/2026.wassa-1.12}
}
```

- [← previous A Parameter-Efficient and Data-Centric Framework for Ancient Chinese Text Recognition and Layout Analysis](https://md.research.elamur.ai/free/en/papers/meng-2026-parameter-efficient-data-centric-framework/)
- [next → A Practical Evaluation Method for Long-Form Simultaneous Speech-to-Speech Translation](https://md.research.elamur.ai/free/en/papers/xue-2026-practical-evaluation-method-long-form/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/20/)

## References

22 references, 9 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Bedour Alrashidi, Amani Jamal, Imtiaz Khan, and Ali Alkhathlan. 2022. A review on abusive content automatic detection: approaches, challenges and opportunities. PeerJ Computer Science, 8:e1142. Publisher: PeerJ Inc. [find](https://scholar.google.com/scholar?q=Bedour+Alrashidi%2C+Amani+Jamal%2C+Imtiaz+Khan%2C+and+Ali+Alkhathlan%2E+2022%2E+A+review+on+abusive+content+automatic+detection%3A+approaches%2C+challenges+and+opportunities%2E+PeerJ+Computer+Science%2C+8%3Ae1142%2E+Publis)
2. Baran Barbarestani, Isa Maks, and Piek Vossen. 2022. Annotating Targets of Toxic Language at the Span Level. In Proceedings of the Third Workshop on Threat, Aggression and Cyberbullying (TRAC 2022), pages 43–51, Gyeongju, Republic of Korea. Association for Computational Linguistics. 17th Internation… [find](https://scholar.google.com/scholar?q=Baran+Barbarestani%2C+Isa+Maks%2C+and+Piek+Vossen%2E+2022%2E+Annotating+Targets+of+Toxic+Language+at+the+Span+Level%2E+In+Proceedings+of+the+Third+Workshop+on+Threat%2C+Aggression+and+Cyberbullying+%28TRAC+2022%29%2C+p)
3. Valerio Basile, Cristina Bosco, Elisabetta Fersini, Debora Nozza, Viviana Patti, Francisco Manuel Rangel Pardo, Paolo Rosso, and Manuela Sanguinetti. 2019. [SemEval-2019 Task 5: Multilingual Detection of Hate Speech Against Immigrants and Women in Twitter](https://md.research.elamur.ai/free/en/papers/basile-2019-semeval-2019-task-5-multilingual/). In Proceedings of the 13th International Wor…
4. 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 Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 14867–14875. Number: 17. [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+Proceedings+of+the+AAA)
5. Jingtao Ding, Yunke Zhang, Yu Shang, Yuheng Zhang, Zefang Zong, Jie Feng, Yuan Yuan, Hongyuan Su, Nian Li, Nicholas Sukiennik, Fengli Xu, and Yong Li. 2025. Understanding World or Predicting Future? A Comprehensive Survey of World Models. ACM Comput. Surv., 58(3):57:1–57:38. [find](https://scholar.google.com/scholar?q=Jingtao+Ding%2C+Yunke+Zhang%2C+Yu+Shang%2C+Yuheng+Zhang%2C+Zefang+Zong%2C+Jie+Feng%2C+Yuan+Yuan%2C+Hongyuan+Su%2C+Nian+Li%2C+Nicholas+Sukiennik%2C+Fengli+Xu%2C+and+Yong+Li%2E+2025%2E+Understanding+World+or+Predicting+Future%3F+A)
6. Mai ElSherief, Caleb Ziems, David Muchlinski, Vaishnavi Anupindi, Jordyn Seybolt, Munmun De Choudhury, and Diyi Yang. 2021. [Latent Hatred: A Benchmark for Understanding Implicit Hate Speech](https://md.research.elamur.ai/free/en/papers/elsherief-2021-latent-hatred-benchmark-understanding-implicit/). In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 345– 363, On…
7. Paula Fortuna and Sérgio Nunes. 2018. A Survey on Automatic Detection of Hate Speech in Text. ACM Computing Surveys, 51(4):1–30. [find](https://scholar.google.com/scholar?q=Paula+Fortuna+and+S%C3%A9rgio+Nunes%2E+2018%2E+A+Survey+on+Automatic+Detection+of+Hate+Speech+in+Text%2E+ACM+Computing+Surveys%2C+51%284%29%3A1%E2%80%9330%2E)
8. Paula Fortuna, Juan Soler, and Leo Wanner. 2020. [Toxic, Hateful, Offensive or Abusive? What Are We Really Classifying? An Empirical Analysis of Hate Speech Datasets](https://md.research.elamur.ai/free/en/papers/fortuna-2020-toxic-hateful-offensive-or-abusive/). In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 6786–6794, Marseille, France. European Language Reso…
9. Nazanin Jafari, James Allan, and Sheikh Muhammad Sarwar. 2024. Target Span Detection for Implicit Harmful Content. In Proceedings of the 2024 ACM SIGIR International Conference on Theory of Information Retrieval, ICTIR ’24, pages 117–122, New York, NY, USA. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=Nazanin+Jafari%2C+James+Allan%2C+and+Sheikh+Muhammad+Sarwar%2E+2024%2E+Target+Span+Detection+for+Implicit+Harmful+Content%2E+In+Proceedings+of+the+2024+ACM+SIGIR+International+Conference+on+Theory+of+Informatio)
10. Md Saroar Jahan and Mourad Oussalah. 2023. A systematic review of hate speech automatic detection using natural language processing. Neurocomputing, 546:126232. [find](https://scholar.google.com/scholar?q=Md+Saroar+Jahan+and+Mourad+Oussalah%2E+2023%2E+A+systematic+review+of+hate+speech+automatic+detection+using+natural+language+processing%2E+Neurocomputing%2C+546%3A126232%2E)
11. Urja Khurana, Ivar Vermeulen, Eric Nalisnick, Marloes Van Noorloos, and Antske Fokkens. 2022. Hate Speech Criteria: A Modular Approach to Task-Specific Hate Speech Definitions. In Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH), pages 176–191, Seattle, Washington (Hybrid). Associa… [find](https://scholar.google.com/scholar?q=Urja+Khurana%2C+Ivar+Vermeulen%2C+Eric+Nalisnick%2C+Marloes+Van+Noorloos%2C+and+Antske+Fokkens%2E+2022%2E+Hate+Speech+Criteria%3A+A+Modular+Approach+to+Task%2DSpecific+Hate+Speech+Definitions%2E+In+Proceedings+of+the+S)
12. Hannah Kirk, Wenjie Yin, Bertie Vidgen, and Paul Röttger. 2023. [SemEval-2023 Task 10: Explainable Detection of Online Sexism](https://md.research.elamur.ai/free/en/papers/kirk-2023-semeval-2023-task-10-explainable/). In Proceedings of the Tin Nguyen, Jiannan Xu, Aayushi Roy, Hal Daumé III, and Marine Carpuat. 2023. Towards Conceptualization of “Fair Explanation”: Disparate Impacts of anti…
13. Nicolás Benjamín Ocampo, Ekaterina Sviridova, Elena Cabrio, and Serena Villata. 2023. An In-depth Analysis of Implicit and Subtle Hate Speech Messages. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 1997–2013, Dubrovnik, Croatia.… [find](https://scholar.google.com/scholar?q=Nicol%C3%A1s+Benjam%C3%ADn+Ocampo%2C+Ekaterina+Sviridova%2C+Elena+Cabrio%2C+and+Serena+Villata%2E+2023%2E+An+In%2Ddepth+Analysis+of+Implicit+and+Subtle+Hate+Speech+Messages%2E+In+Proceedings+of+the+17th+Conference+of+the+Eur)
14. John Pavlopoulos, Jeffrey Sorensen, Léo Laugier, and Ion Androutsopoulos. 2021. [SemEval-2021 Task 5: Toxic Spans Detection](https://md.research.elamur.ai/free/en/papers/pavlopoulos-2021-semeval-2021-task-5-toxic/). In Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), pages 59–69, Online. Association for Computational Linguistics.
15. Rahul Pradhan, Ankur Chaturvedi, Aprna Tripathi, and Dilip Kumar Sharma. 2020. A Review on Offensive Language Detection. In Mohan L. Kolhe, Shailesh Tiwari, Munesh C. Trivedi, and Krishn K. Mishra, editors, Advances in Data and Information Sciences, volume 94, pages 433–439. Springer Singapore, Sing… [find](https://scholar.google.com/scholar?q=Rahul+Pradhan%2C+Ankur+Chaturvedi%2C+Aprna+Tripathi%2C+and+Dilip+Kumar+Sharma%2E+2020%2E+A+Review+on+Offensive+Language+Detection%2E+In+Mohan+L%2E+Kolhe%2C+Shailesh+Tiwari%2C+Munesh+C%2E+Trivedi%2C+and+Krishn+K%2E+Mishra%2C+ed)
16. Paul Röttger, Bertie Vidgen, Dirk Hovy, and Janet Pierrehumbert. 2022. [Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks](https://md.research.elamur.ai/free/en/papers/rottger-2022-two-contrasting-data-annotation-paradigms/). In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 175–190,…
17. Bertie Vidgen and Leon Derczynski. 2020. Directions in abusive language training data, a systematic review: Garbage in, garbage out. PLOS ONE, 15(12):e0243300. Publisher: Public Library of Science. [find](https://scholar.google.com/scholar?q=Bertie+Vidgen+and+Leon+Derczynski%2E+2020%2E+Directions+in+abusive+language+training+data%2C+a+systematic+review%3A+Garbage+in%2C+garbage+out%2E+PLOS+ONE%2C+15%2812%29%3Ae0243300%2E+Publisher%3A+Public+Library+of+Science%2E)
18. Bertie Vidgen, Dong Nguyen, Helen Margetts, Patricia Rossini, and Rebekah Tromble. 2021. [Introducing CAD: the Contextual Abuse Dataset](https://md.research.elamur.ai/free/en/papers/vidgen-2021-introducing-cad-contextual-abuse-dataset/). In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2289–2303,…
19. Zeerak Waseem, Thomas Davidson, Dana Warmsley, and Ingmar Weber. 2017. [Understanding Abuse: A Typology of Abusive Language Detection Subtasks](https://md.research.elamur.ai/free/en/papers/waseem-2017-understanding-abuse-typology-abusive-language/). In Proceedings of the First Workshop on Abusive Language Online, pages 78–84, Vancouver, BC, Canada. Association for Computational Linguistics.
20. Zeerak Waseem and Dirk Hovy. 2016. [Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter](https://md.research.elamur.ai/free/en/papers/waseem-2016-hateful-symbols-or-hateful-people/). In Proceedings of the NAACL Student Research Workshop, pages 88– 93, San Diego, California. Association for Computational Linguistics.
21. Ilker Yildirim and L.A. Paul. 2024. From task structures to world models: what do LLMs know? Trends in Cognitive Sciences, 28(5):404–415. [find](https://scholar.google.com/scholar?q=Ilker+Yildirim+and+L%2EA%2E+Paul%2E+2024%2E+From+task+structures+to+world+models%3A+what+do+LLMs+know%3F+Trends+in+Cognitive+Sciences%2C+28%285%29%3A404%E2%80%93415%2E)
22. Xinchen Yu, Eduardo Blanco, and Lingzi Hong. 2022. Hate Speech and Counter Speech Detection: Conversational Context Does Matter. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5918–5930, Seattle… [find](https://scholar.google.com/scholar?q=Xinchen+Yu%2C+Eduardo+Blanco%2C+and+Lingzi+Hong%2E+2022%2E+Hate+Speech+and+Counter+Speech+Detection%3A+Conversational+Context+Does+Matter%2E+In+Proceedings+of+the+2022+Conference+of+the+North+American+Chapter+of+)

*Updated 1 November 2026*