@inproceedings{zhang-etal-2025-alleviating,
    title = "Alleviating Hallucinations of Large Language Models through Induced Hallucinations",
    author = "Zhang, Yue  and
      Cui, Leyang  and
      W., V.  and
      Shi, Shuming",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.findings-naacl.459/",
    pages = "8218--8232",
    ISBN = "979-8-89176-195-7",
    abstract = "Despite their impressive capabilities, large language models (LLMs) have been observed to generate responses that include inaccurate or fabricated information, a phenomenon commonly known as hallucination. In this work, we propose a simple Induce-then-Contrast Decoding (ICD) strategy to alleviate hallucinations. We first construct a factually weak LLM by inducing hallucinations from the original LLMs. Then, we penalize these induced hallucinations during decoding to enhance the factuality of the generated content. Concretely, we determine the final next-token predictions by amplifying the predictions from the original model and downplaying the induced untruthful predictions via contrastive decoding. Experimental results on both discrimination-based and generation-based hallucination evaluation benchmarks, such as TruthfulQA and FActScore, demonstrate that our proposed ICD methods can effectively enhance the factuality of LLMs across various task formats, model sizes, and model families. For example, when equipped with ICD, Llama2-7B-Chat and Mistral-7B-Instruct achieve performance comparable to ChatGPT and GPT4 on TruthfulQA, respectively, without compromising their generalization capabilities on other tasks."
}