@inproceedings{kapoor-etal-2026-dqa,
    title = "{DQA}: Diagnostic Question Answering for {IT} Support",
    author = "Kapoor, Vishaal  and
      Dundua, Mariam  and
      Yortucboylu, Evren  and
      Ahuja, Sarthak  and
      Kordjazi, Neda  and
      Li, Yiming  and
      padala, Vaibhavi  and
      Ho, Derek  and
      Whitted, Jennifer  and
      Steinert, Rebecca",
    editor = "Li, Yunyao  and
      Rehm, Georg  and
      Tu, Mei",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-industry.79/",
    pages = "1128--1135",
    ISBN = "979-8-89176-394-4",
    abstract = "Enterprise IT support interactions are fundamentally diagnostic: effective resolution requires iterative evidence gathering from ambiguous user reports to identify an underlying root cause. While retrieval-augmented generation (RAG) provides grounding through historical cases, standard multi-turn RAG systems lack explicit diagnostic state and therefore struggle to accumulate evidence and resolve competing hypotheses across turns.We introduce DQA, a diagnostic question-answering framework that maintains persistent diagnostic state and aggregates retrieved cases at the level of root causes rather than individual documents. DQA combines conversational query rewriting, retrieval aggregation, and state-conditioned response generation to support systematic troubleshooting under enterprise latency and context constraints.We evaluate DQA on 150 anonymized enterprise IT support scenarios using a replay-based protocol. Averaged over three independent runs, DQA achieves a 78.7{\%} success rate under a trajectory-level success criterion, compared to 41.3{\%} for a multi-turn RAG baseline, while reducing average turns from 8.4 to 3.9. This improvement reflects the benefit of explicitly representing competing explanations and aggregating evidence across turns in unscripted troubleshooting."
}