Vivatham: a multi-agent debate framework for generating counter-narratives against homophobia and transphobia in Tamil
Open Access
- 14 August 2026
- journal article
- research article
- Published by Springer Nature in Social Network Analysis and Mining
- Vol. 16 (1)
Abstract
Social media platforms have increasingly become conduits for the dissemination of hate speech targeting the LGBTQ+ community, significantly undermining their mental health and overall well-being. This phenomenon presents a critical challenge within the field of Natural Language Processing (NLP). While hate speech detection is a well-established area of research, counter-narratives (CNs)-defined as polite, empathetic responses designed to neutralize harmful content-offer a promising alternative to traditional moderation. However, the availability of CN datasets remains severely limited for low-resource Dravidian languages, such as Tamil. In this paper, we introduce a newly curated dataset comprising 5,428 Tamil HS-CN pairs and propose VIVATHAM, a novel multi-agent persona debate framework for generating high quality Tamil counter-narratives. This dataset was developed through a human-in-the-loop (HITL) process, in which domain experts reviewed and refined initial CNs to ensure linguistic accuracy, politeness, and cultural sensitivity. Unlike conventional methods, our approach employs a system of agents with distinct personas to debate and iteratively refine responses from diverse perspectives. This debate-based mechanism facilitates the production of nuanced, non-aggressive, and contextually appropriate counter-narratives. Our results demonstrate that the multi-agent debate framework significantly outperforms standard CN generation approaches. This research contributes the first large-scale Tamil CN dataset and highlights the potential of multi-agent systems to enhance the quality and inclusiveness of online discourse. GitHub Link: https://github.com/Unit-for-Inclusive-AI/VIVATHAM .Keywords
Funding Information
- Research Ireland (SFI/12/RC/2289 P2 (Insight).)
This publication has 28 references indexed in Scilit:
- An information retrieval language model-based zero- and few-shot learning for propaganda detection in social media contentKnowledge and Information Systems, 2026
- Misinformation detection on online social networks using pretrained language modelsInformation Processing & Management, 2025
- Public opinion prediction on social media by using machine learning methodsExpert Systems with Applications, 2025
- Empowering Smart Education in the Age of Smart Cities: Combating Fake News and Misinformation Through Propaganda Text Analysis2024
- From hate speech to HateLess. The effectiveness of a prevention program on adolescents’ online hate speech involvementComputers in Human Behavior, 2024
- Homophobia and transphobia detection for low-resourced languages in social media commentsNatural Language Processing Journal, 2023
- Detection of homophobia and transphobia in YouTube commentsInternational Journal of Data Science and Analytics, 2023
- Hate speech and offensive language detection in Dravidian languages using deep ensemble frameworkComputer Speech & Language, 2022
- Gender Differences in Correlates of Homophobia and TransphobiaSex Roles, 2008
- Homophobia: Conceptual, definitional, and value issuesJournal of Psychopathology and Behavioral Assessment, 1993