RspectNLP@LT-EDI 2026:Rubric-Driven Prompting for Safe Multilingual Counter Narrative Generation
Year: 2026
Type: conference-paper
Abstract: The problem of harmful online discourse against the LGBTQ+ community is still a concern on social media platforms.Although hate speech detection is a well-explored area, the task of constructive counter-narrative generation is still an emerging field of research, especially in the multilingual and low-resource settings.Counter-narratives are designed to counter harmful discourse with respectful and empathetic responses, as opposed to mere content deletion.In this paper, the model proposes a zero-shot multilingual system for counter-narrative generation in English and Tamil.The proposed system employs the pretrained google/flan-t5-base transformer model guided by rubric-aligned prompts to encourage politeness, contextual relevance, and non-toxic response generation.The system operates in a zero-shot setting without taskspecific fine-tuning and uses beam search decoding for controlled response generation.On the English test data, the system scored an overall score of 70.33 per cent with a contextual coherence score of 81.82 per cent.On the Tamil test data, the system scored an overall score of 33.57per cent with significantly lower scores on coherence and quality.These findings indicate that structured prompting can facilitate safe and coherent generation in English, but also underscore the challenges of zero-shot multilingual models in low-resource language scenarios.
Authors: S.b.priya, Bharathi B
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Reduced inequalities
Open Access status: hybrid
OpenAlex ID: W7166803764