@inproceedings{agrahari-etal-2026-know,
    title = "{I} know you are different! Towards Persona Driven Knowledge-infused Dialogue Assistant",
    author = "Agrahari, Shifali  and
      Mahato, Moushumi  and
      Tiwari, Abhisek  and
      Nabi, Javaid",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2026.eacl-long.96/",
    pages = "2181--2205",
    ISBN = "979-8-89176-380-7",
    abstract = "Despite advances in large language models (LLMs), Task-Oriented Dialogue (TOD) systems often fall short in delivering personalized, context-rich responses, especially in low-resource, code-mixed, and multimodal settings like Hinglish (Hindi-English). To bridge this gap, we introduce \textit{HiVisTask}, the first Hinglish multimodal, multidomain, persona-based TOD dataset that captures user-agent interactions across text and visual modalities. We also propose \textit{$G^3 TOD$}, a generalizable framework that enhances personalization using three structured knowledge graphs: entity context, user persona, and commonsense reasoning, all extracted from conversation history. Extensive experiments with LLMs (e.g., LLaMA3.2, Phi3, GPT4, Mistral7b, Qwen3, Gemma3) show that \textit{$G^3 TOD$} consistently outperforms both standard and ablated baselines. We observe substantial gains across evaluation metrics (both quantitative: BLEU {\textuparrow} and qualitative: Human Eval {\textuparrow}) over existing models. The observed improvements strongly underscore the value of structured and selective contextualization in generating personalized and engaging multimodal responses."
}