@inproceedings{wang-etal-2026-benchmarking-failure,
    title = "From Benchmarking to Failure Diagnosis: Diagnosing Classical {C}hinese Understanding in {LLM}s via {IRT} and Error Attribution",
    author = "Wang, Jiong  and
      Li, Tengju  and
      Yu, Shengquan",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-emnlp.618/",
    doi = "10.18653/2026.findings-emnlp.618",
    pages = "12991--13005",
    ISBN = "979-8-89176-462-0"
}