@inproceedings{s-etal-2026-igniters,
    title = "Igniters@{LTEDI} 2026: Multilingual Gender-Inclusive Language Generation with m{T}5 and Counter-Narrative Generation Using Llama-3",
    author = "S, Rajendran  and
      N, Ramkumar  and
      R, Malarselvi",
    editor = "Chakravarthi, Bharathi Raja  and
      B, Bharathi  and
      Durairaj, Thenmozhi  and
      Garc{\'i}a Cumbreras, Miguel {\'A}ngel  and
      Jim{\'e}nez-Zafra, Salud Mar{\'i}a",
    booktitle = "Proceedings of the Sixth Workshop on Language Technology for Equality, Diversity, Inclusion",
    month = jul,
    year = "2026",
    address = "Virtual (Online)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl-awards/2026.ltedi-1.18/",
    doi = "10.18653/v1/2026.ltedi-1.18",
    pages = "172--176",
    ISBN = "979-8-89176-424-8",
    abstract = "The deployment of Large Language Models(LLMs) has intensified concerns regarding the propagation of societal stereotypes encoded with webscale training corpora. This paper presents a dual-paradigm framework specially designed to address multilingual gender-inclusvity and counterfactual generation. For multilingual gender-neutral text transformation,a fine-tuned mT5 encoder{--}decoder model performs controlled sentence rewriting with minimal edits while preserving semantic fidelity and grammatical fluency. For counter-narrative generation, the Llama-3 8B decoder-only model is employed to generate empathetic and persuasive responses through structured prompt-based generation. The framework is evaluated using datasets from the LT-EDI ACL 2026 sharedtask across multiple languages, including English, Tamil, Kannada, German, and Spanish. Experimental results demonstrate strong effectiveness in identifying and neutralizing gender markers, particularly in morphologically rich languages, while the counter-narrative component achieves high performance in politeness, coherence, and relevance. Overall, the proposed approach contributes toward the development of responsible and inclusive multilingual NLP systems."
}