JusticeBots@LT-EDI 2026: Prompt-Based Counter-Narrative Generation for Homophobia and Transphobia Comments
Year: 2026
Type: conference-paper
Abstract: Online platforms increasingly host hate speech targeting marginalized communities, including homophobic and transphobic comments directed at LGBTQ+ individuals.Counternarratives provide a constructive way to respond to harmful speech by promoting empathy, factual clarification, and respectful dialogue.In this work, we participate in the Shared Task on Counter-Narrative Generation on Homophobic and Transphobic Comments at LT-EDI @ ACL 2026.We adopt a zero-shot prompting approach using large language models accessed through publicly available AI tools, including GPT-4o, Gemini 1.5 Pro, and Llama-3 Sonar Large via Perplexity AI.Instead of training a task-specific model, we design a structured prompt that guides the models to generate respectful, concise, and contextually appropriate counter-narratives.Experiments were conducted on English and Tamil comments provided by the organizers.Results demonstrate that prompt-based generation can produce meaningful multilingual counter-narratives without additional training.Our approach highlights the potential of large language models as lightweight tools for counter-speech generation in multilingual online environments.
Institution: Sri Sivasubramaniya Nadar College of Engineering
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Reduced inequalities
Open Access status: hybrid
OpenAlex ID: W7166884951