@inproceedings{sun-etal-2026-large-language,
    title = "Large Language Models Are Still Misled by Simple Bias Ensembles",
    author = "Sun, Zhouhao  and
      Kan, Zhiyuan  and
      Ding, Xiao  and
      Du, Li  and
      Cai, Bibo  and
      Zhao, Yang  and
      Qin, Bing  and
      Liu, Ting",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.971/",
    pages = "19444--19455",
    ISBN = "979-8-89176-395-1",
    abstract = "With the evolution of large language models (LLMs), their robustness against individual simple biases has been enhanced. However, we observe that the ensemble of multiple simple biases still exerts a significant adverse impact on LLMs. Given that real-world data samples are typically confounded by a wide range of biases, LLMs tend to exhibit unstable performance when deployed in high-stakes real-world scenarios such as clinical diagnosis and legal document analysis. However, previous benchmarks are constrained to datasets where each sample is manually injected with only one type of bias. To bridge this gap, we propose a multi-bias benchmark where each sample contains multiple types of biases. Experimental results reveal that existing LLMs and debiasing methods perform poorly on this benchmark, highlighting the challenge of eliminating such compounded biases."
}