The Proceedings of the workshop are published at https://coling-2025-proceedings.s3.us-east-1.amazonaws.com/workshops/MCG/program.html
While interest in automatic approaches to Counterspeech generation has been steadily growing, including studies on data curation [1, 2], detection [3, 4], and generation [5, 6, 7, 8], the large majority of the published experimental work on automatic Counterspeech generation has been carried out for English. This is due to the scarcity of both non-English manually curated training data and to the crushing predominance of English in the generative Large Language Models (LLMs) ecosystem. A workshop on exploring Multilingual Counterspeech Generation is proposed to promote and encourage research on multilingual approaches for this challenging topic.
As mentioned above, research on automatic generation has mostly focused on the collection and generation of contraphones for English, but there have also been some efforts to develop contraphone datasets for Italian [1,9], French [1], Spanish [10, 11, 12] and Basque [12], which can be used to facilitate research on automatic counter-speech generation from a multilingual point of view.
Thus, this workshop aims to test monolingual and multilingual LLMs in particular and Language Technology in general to automatically generate counterspeech not only in English but also in languages with fewer resources. In this sense, an important goal of the workshop will be to understand the impact of using LLMs, considering for example how to deal with pressing issues such as biases, data scarcity, hallucinated content or data contamination.
We seek to maximize the scientific and social impact of this workshop by promoting the creation of a community of researchers from diverse fields, such as computer and social sciences, as well as policy makers and other stakeholders interested in automatic counterspeech generation. By doing so we aim to gain a deeper understanding of how counterspeech is currently used to tackle abuse by individuals, activists, and organizations and how Natural Language Processing (NLP) and Generation (NLG) may be best applied to counteract it.
The following schedule is tentative and subject to change.
All times are in Gulf Standard Time (UTC+04:00).
All presentations will take place via Zoom; connection details will be provided to registered participants.
9:00 - 9:15
9:15 - 9:35
Damian Ariel Furman, Pablo Torres, José A. Rodríguez, Diego Letzen, Maria Vanina Martinez and Laura Alonso Alemany
9:35 - 9:55
Michael Bennie, Demi Zhang, Bushi Xiao, Jing Cao, Chryseis Xinyi Liu, Jian Meng and Alayo Tripp
9:55 - 10:20
10:30 - 11:00
11:00 - 11:40
Abstract: As hate proliferates online, counterspeech has emerged as a powerful grassroots effort to combat hate without direct censorship, yet manually countering hate speech is challenging. However, automatic counterspeech generation could also backfire. In this talk, I will discuss my lab's recent work on AI and counterspeech. I will first give insights from the first participatory study investigating the perspectives of active and possibly future counterspeakers on AI's involvement in counterspeech, highlighting what counter speakers want and do not want AI to do. Then, building upon these insights, I will discuss recent investigations towards providing LLM-generated counterspeech suggestions that counter underlying stereotypical implications of statements, beyond simply denouncing hate. Finally, I will discuss open challenges and future investigations towards more counterspeaker-centric AI efforts in counterspeech.
11:40 - 11:55
David Salvador Márquez, Helena Montserrat Gómez Adorno, Ilia Markov and Selene Báez Santamaría
11:55 - 12:10
Sahil Wadhwa, Chengtian Xu, Haoming Chen, Aakash Mahalingam, Akankshya Kar and Divya Chaudhary
12:10 - 12:25
Daniel Russo
12:30 - 14:00
14:00 - 14:15
Michael Bennie, Bushi Xiao, Chryseis Xinyi Liu, Demi Zhang and Jian Meng
14:15 - 14:30
Xinglin Lyu, Haolin Wang, Min Zhang and Hao Yang
14:30 - 14:45
Md Shariq Farhan
14:45 - 15:00
Emanuele Moscato, Arianna Muti and Debora Nozza
15:00 - 15:30
15:30 - 16:00
16:00 - 16:45
Abstract: The "Get the Trolls Out" (GTTO) project addresses the pressing challenge of religious hate speech and discrimination in European digital and traditional media space. By empowering civil society actors, GTTO combines media monitoring, education, and advocacy to combat hate speech and foster inclusive narratives. This presentation provides an overview of the project’s innovative activities, including hate speech monitoring, reporting, and the development of impactful counter-narratives. Highlighting successful collaborations with civil society organisations and journalists, it demonstrates practical approaches to dismantling harmful stereotypes and fostering interfaith dialogue.
16:45 - 17:00
Topics of interest include, but are not limited to:
Models and methods for generating counter-speech in different languages.
Automatic Counterspeech generation for low resource languages with scarce training data.
Dialogue agents that use counterspeech to combat offensive messages that are directed to individuals or groups, targeted based on various aspects such as ideology, gender, sexual orientation and religion.
Methods for human and automatic evaluation of counterspeech.
Multidisciplinary studies providing different perspectives on the topic such as computer science, social science, psychology, etc.
Development of taxonomies and quality datasets for counterspeech in multiple languages.
Potentials and limitations (e.g., fairness, biases, hallucinated content) of applying different NLP methods, such as LLMs, to generate counterspeech.
Social impact and empirical studies of counterspeech in social networks, including research on the effectiveness and consequences for users of using counterspeech to combat hate online.
We welcome two types of papers: regular workshop papers and non-archival submissions. Regular workshop papers will be included in the workshop proceedings. All submissions must be in PDF format and made through START
Regular workshop papers: Authors can submit papers up to 8 pages, with unlimited pages for references. Authors may submit up to 100 MB of supplementary materials separately and their code for reproducibility. All submissions undergo an double-blind single-track review. Accepted papers will be presented as posters with the possibility of oral presentations.
Non-archival submissions: Cross-submissions are welcome. Accepted papers in other venues or journals will be presented at the workshop, but will not be included in the workshop proceedings. Papers must be in PDF format and will be reviewed in a double-blind fashion by workshop reviewers. We also welcome extended abstracts (up to 2 pages) of papers that are work in progress, under review or to be submitted to other venues. Papers in this category need to follow the COLING format.
Nov 20th
Nov 25th
Dec 2nd
Dec 8th
Dec 10th
Dec 13th
Jan 19th
Important: All deadlines are at 23:59 UTC-12 (Anywhere on Earth, AoE Time Zone).
Submissions should follow COLING 2025 Author Guidelines and policies for submission, review and citation, and be anonymised for double blind reviewing. Please use COLING 2025 style files; LaTeX style files and Microsoft Word templates are available at https://coling2025.org/calls/submission_guidlines/.
Rodrigo Agerri, HiTZ Center - Ixa, University of the Basque Country UPV/EHU (Spain)
Helena Bonaldi, Fondazione Bruno Kessler (Italy)
Marco Guerini, Fondazione Bruno Kessler (Italy)
María Teresa Martín-Valdivia, University of Jaén (Spain)
Arturo Montejo-Ráez, University of Jaén (Spain)
Aitor Soroa, HiTZ Center – Ixa, University of the Basque Country UPV/EHU (Spain)
María Estrella Vallecillo-Rodríguez, University of Jaén (Spain)
Irune Zubiaga, HiTZ Center – Ixa, University of the Basque Country (Spain)
Yi-Ling Chung, Elizaveta Kuzmenko, Serra Sinem Tekiroğlu, and Marco Guerini. 2019a. CONAN-COunter NArratives through nichesourcing: a multilingual dataset of responses to fight online hate speech. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2819–2829, Florence, Italy. Association for Computational Linguistics.
Margherita Fanton, Helena Bonaldi, Serra Sinem Tekiroğlu, and Marco Guerini. 2021. Human-in-the-loop for data collection: a multi-target counter narrative dataset to fight online hate speech. In 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), pages 3226–3240, Online. Association for Computational Linguistics.
Yi-Ling Chung, Marco Guerini, and Rodrigo Agerri. 2021a. Multilingual counter narrative type classification. In Proceedings of the 8th Workshop on Argument Mining, pages 125–132, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Binny Mathew, Hardik Tharad, Subham Rajgaria, Prajwal Singhania, Suman Kalyan Maity, Pawan Goyal, and Animesh Mukherjee. 2018. Thou shalt not hate: Countering online hate speech. In International Conference on Web and Social Media.
Serra Sinem Tekiroğlu, Yi-Ling Chung, and Marco Guerini. 2020. Generating counter narratives against online hate speech: Data and strategies. In ACL.
Yi-Ling Chung, Serra Sinem Tekiroğlu, and Marco Guerini. 2021b. Towards knowledge-grounded counter narrative generation for hate speech. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 899–914, Online. Association for Computational Linguistics.
Wanzheng Zhu and Suma Bhat. 2021. Generate, prune, select: A pipeline for counterspeech generation against online hate speech. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 134–149, Online. Association for Computational Linguistics.
Serra Sinem Tekiroğlu, Helena Bonaldi, Margherita Fanton, and Marco Guerini. 2022. Using pre-trained language models for producing counter narratives against hate speech: a comparative study. In Findings of the Association for Computational Linguistics: ACL 2022, pages 3099–3114, Dublin, Ireland. Association for Computational Linguistics.
Yi-Ling Chung, Serra Sinem Tekiroğlu, and Marco Guerini. 2020. Italian Counter Narrative Generation to Fight Online Hate Speech. In Proceedings of the Seventh Italian Conference on Computational Linguistics CLiC-it.
Maria Estrella Vallecillo-Rodríguez, Arturo Montejo-Raéz, and Maria Teresa Martín-Valdivia. 2023. Automatic counter-narrative generation for hate speech in Spanish. In Procesamiento del Lenguaje Natural Volume 71, pages 227-245, Online.
María Estrella Vallecillo Rodríguez, Maria Victoria Cantero Romero, Isabel Cabrera De Castro, Arturo Montejo Ráez, and María Teresa Martín Valdivia. 2024. CONAN-MT-SP: A Spanish Corpus for Counternarrative Using GPT Models. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 3677–3688, Torino, Italia. ELRA and ICCL.
Jaione Bengoetxea, Yi-Ling Chung, Marco Guerini, and Rodrigo Agerri. 2024. Basque and Spanish Counter Narrative Generation: Data Creation and Evaluation. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 2132–2141, Torino, Italia. ELRA and ICCL.