@inproceedings{han-etal-2025-exploring,
    title = "Exploring the Impact of Instruction-Tuning on {LLM}{'}s Susceptibility to Misinformation",
    author = "Han, Kyubeen  and
      Jang, Junseo  and
      Kim, Hongjin  and
      Jeong, Geunyeong  and
      Kim, Harksoo",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.1295/",
    pages = "26711--26731",
    ISBN = "979-8-89176-251-0",
    abstract = "Instruction-tuning enhances the ability of large language models (LLMs) to follow user instructions more accurately, improving usability while reducing harmful outputs. However, this process may increase the model{'}s dependence on user input, potentially leading to the unfiltered acceptance of misinformation and the generation of hallucinations. Existing studies primarily highlight that LLMs are receptive to external information that contradict their parametric knowledge, but little research has been conducted on the direct impact of instruction-tuning on this phenomenon. In our study, we investigate the impact of instruction-tuning on LLM susceptibility to misinformation. Our analysis reveals that instruction-tuned LLMs are significantly more likely to accept misinformation when it is presented by the user. A comparison with base models shows that instruction-tuning increases reliance on user-provided information, shifting susceptibility from the assistant role to the user role. Furthermore, we explore additional factors influencing misinformation susceptibility, such as the role of the user in prompt structure, misinformation length, and the presence of warnings in the system prompt. Our findings underscore the need for systematic approaches to mitigate unintended consequences of instruction-tuning and enhance the reliability of LLMs in real-world applications."
}