@inproceedings{zhu-mandivarapu-2024-trustful,
    title = "Trustful {LLM}s: Customizing and Grounding Text Generation with knowledge bases and Dual Decoders",
    author = "Zhu, Xiaofeng  and
      Mandivarapu, Jaya Krishna",
    editor = "Kumar, Sachin  and
      Balachandran, Vidhisha  and
      Park, Chan Young  and
      Shi, Weijia  and
      Hayati, Shirley Anugrah  and
      Tsvetkov, Yulia  and
      Smith, Noah  and
      Hajishirzi, Hannaneh  and
      Kang, Dongyeop  and
      Jurgens, David",
    booktitle = "Proceedings of the 1st Workshop on Customizable NLP: Progress and Challenges in Customizing NLP for a Domain, Application, Group, or Individual (CustomNLP4U)",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.customnlp4u-1.13/",
    doi = "10.18653/v1/2024.customnlp4u-1.13",
    pages = "156--166",
    abstract = "Although people are impressed by the content generation skills of large language models, the use of LLMs, such as ChatGPT, is limited by the domain grounding of the content. The correctness and groundedness of the generated content need to be based on a verified context, such as results from Retrieval-Augmented Generation (RAG). One important issue when adapting LLMs to a customized domain is that the generated responses are often incomplete, or the additions are not verified and may even be hallucinated. Prior studies on hallucination detection have focused on evaluation metrics, which are not easily adaptable to dynamic domains and can be vulnerable to attacks like jail-breaking. In this work, we propose 1) a post-processing algorithm of leveraging knowledge triplets in RAG context to correct hallucinations and 2) a dual-decoder model that fuses RAG context to guide the generation process."
}