@inproceedings{luo-etal-2024-zero-resource,
    title = "Zero-Resource Hallucination Prevention for Large Language Models",
    author = "Luo, Junyu  and
      Xiao, Cao  and
      Ma, Fenglong",
    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/jlcl-multiple-ingestion/2024.findings-emnlp.204/",
    doi = "10.18653/v1/2024.findings-emnlp.204",
    pages = "3586--3602",
    abstract = "The prevalent use of large language models (LLMs) in various domains has drawn attention to the issue of {\textquotedblleft}hallucination{\textquotedblright}, which refers to instances where LLMs generate factually inaccurate or ungrounded information. Existing techniques usually identify hallucinations post-generation that cannot prevent their occurrence and suffer from inconsistent performance due to the influence of the instruction format and model style. In this paper, we introduce a novel pre-detection self-evaluation technique, referred to as SELF-FAMILIARITY, which focuses on evaluating the model`s familiarity with the concepts present in the input instruction and withholding the generation of response in case of unfamiliar concepts under the zero-resource setting, where external ground-truth or background information is not available. We also propose a new dataset Concept-7 focusing on the hallucinations caused by limited inner knowledge. We validate SELF-FAMILIARITY across four different large language models, demonstrating consistently superior performance compared to existing techniques. Our findings propose a significant shift towards preemptive strategies for hallucination mitigation in LLM assistants, promising improvements in reliability, applicability, and interpretability."
}