@inproceedings{zhao-etal-2025-know,
    title = "Do We Know What {LLM}s Don{'}t Know? A Study of Consistency in Knowledge Probing",
    author = {Zhao, Raoyuan  and
      K{\"o}ksal, Abdullatif  and
      Modarressi, Ali  and
      Hedderich, Michael A.  and
      Schuetze, Hinrich},
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.1263/",
    doi = "10.18653/v1/2025.findings-emnlp.1263",
    pages = "23254--23280",
    ISBN = "979-8-89176-335-7",
    abstract = "The reliability of large language models (LLMs) is greatly compromised by their tendency to hallucinate, underscoring the need for precise identification of knowledge gaps within LLMs. Various methods for probing such gaps exist, ranging from calibration-based to prompting-based methods. To evaluate these probing methods, in this paper, we propose a new process based on using input variations and quantitative metrics. Through this, we expose two dimensions of inconsistency in knowledge gap probing. (1) **Intra-method inconsistency:** Minimal non-semantic perturbations in prompts lead to considerable variance in detected knowledge gaps within the same probing method; e.g., the simple variation of shuffling answer options can decrease agreement to around 40{\%}. (2) **Cross-method inconsistency:** Probing methods contradict each other on whether a model knows the answer. Methods are highly inconsistent {--} with decision consistency across methods being as low as 7{\%} {--} even though the model, dataset, and prompt are all the same. These findings challenge existing probing methods and highlight the urgent need for perturbation-robust probing frameworks."
}