@inproceedings{long-etal-2024-trust,
    title = "Trust in Internal or External Knowledge? Generative Multi-Modal Entity Linking with Knowledge Retriever",
    author = "Long, Xinwei  and
      Zeng, Jiali  and
      Meng, Fandong  and
      Zhou, Jie  and
      Zhou, Bowen",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.findings-acl.450/",
    doi = "10.18653/v1/2024.findings-acl.450",
    pages = "7559--7569",
    abstract = "Multi-modal entity linking (MEL) is a challenging task that requires accurate prediction of entities within extensive search spaces, utilizing multi-modal contexts. Existing generative approaches struggle with the knowledge gap between visual entity information and the intrinsic parametric knowledge of LLMs. To address this knowledge gap, we introduce a novel approach called GELR, which incorporates a knowledge retriever to enhance visual entity information by leveraging external sources. Additionally, we devise a prioritization scheme that effectively handles noisy retrieval results and manages conflicts arising from the integration of external and internal knowledge. Moreover, we propose a noise-aware instruction tuning technique during training to finely adjust the model{'}s ability to leverage retrieved information effectively. Through extensive experiments conducted on three benchmarks, our approach showcases remarkable improvements, ranging from 3.0{\%} to 6.5{\%}, across all evaluation metrics compared to strong baselines. These results demonstrate the effectiveness and superiority of our proposed method in tackling the complexities of multi-modal entity linking."
}