@inproceedings{lee-etal-2024-stark,
    title = "Stark: Social Long-Term Multi-Modal Conversation with Persona Commonsense Knowledge",
    author = "Lee, Young-Jun  and
      Lee, Dokyong  and
      Youn, Junyoung  and
      Oh, Kyeong-Jin  and
      Ko, Byungsoo  and
      Hyeon, Jonghwan  and
      Choi, Ho-Jin",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.findings-emnlp.708/",
    doi = "10.18653/v1/2024.findings-emnlp.708",
    pages = "12137--12162",
    abstract = "Humans share a wide variety of images related to their personal experiences within conversations via instant messaging tools. However, existing works focus on (1) image-sharing behavior in singular sessions, leading to limited long-term social interaction, and (2) a lack of personalized image-sharing behavior. In this work, we introduce , a large-scale long-term multi-modal dialogue dataset that covers a wide range of social personas in a multi-modality format, time intervals, and images. To construct automatically, we propose a novel multi-modal contextualization framework, , that generates long-term multi-modal dialogue distilled from ChatGPT and our proposed image aligner. Using our , we train a multi-modal conversation model, 7B, which demonstrates impressive visual imagination ability. Furthermore, we demonstrate the effectiveness of our dataset in human evaluation. The code, dataset, and model will be publicly released after publication."
}