@article{watawana-etal-2026-consistency,
    title = "When Consistency Becomes Bias: Interviewer Effects in Semi-Structured Clinical Interviews",
    author = "Watawana, Hasindri Sankalpana  and
      Burdisso, Sergio Gast{\'o}n  and
      Moreno-Galvan, Diego Aaron  and
      Sanchez-Vega, Fernando  and
      Lopez Monroy, Adrian Pastor  and
      Motlicek, Petr  and
      Villatoro-Tello, Esau",
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    journal = "International Conference on Language Resources and Evaluation",
    volume = "main",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/ingest-lrec/2026.lrec-main.185/",
    pages = "2355--2361",
    abstract = "Automatic depression detection from doctor{--}patient conversations has gained momentum thanks to the availability of public corpora and advances in language modeling. However, interpretability remains limited: strong performance is often reported without revealing what drives predictions. We analyze three datasets{---}ANDROIDS, DAIC-WOZ, and E-DAIC{---}and identify a systematic bias from interviewer prompts in semi-structured interviews. Models trained on interviewer turns exploit fixed prompts and positions to distinguish depressed from control subjects, often achieving high classification scores without using participant language. Restricting models to participant utterances distributes decision evidence more broadly and reflects genuine linguistic cues. While semi-structured protocols ensure consistency, including interviewer prompts inflates performance by leveraging script artifacts. Our results highlight a cross-dataset, architecture-agnostic bias and emphasize the need for analyses that localize decision evidence by time and speaker to ensure models learn from participants' language."
}