DQA: Diagnostic Question Answering for IT Support
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908948998651904 |
|---|---|
| author | Kapoor, Vishaal Dundua, Mariam Ahuja, Sarthak Kordjazi, Neda Yortucboylu, Evren Padala, Vaibhavi Ho, Derek Whitted, Jennifer Steinert, Rebecca |
| author_facet | Kapoor, Vishaal Dundua, Mariam Ahuja, Sarthak Kordjazi, Neda Yortucboylu, Evren Padala, Vaibhavi Ho, Derek Whitted, Jennifer Steinert, Rebecca |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_05350 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DQA: Diagnostic Question Answering for IT Support Kapoor, Vishaal Dundua, Mariam Ahuja, Sarthak Kordjazi, Neda Yortucboylu, Evren Padala, Vaibhavi Ho, Derek Whitted, Jennifer Steinert, Rebecca Computation and Language Artificial Intelligence I.2.7 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. |
| title | DQA: Diagnostic Question Answering for IT Support |
| topic | Computation and Language Artificial Intelligence I.2.7 |
| url | https://arxiv.org/abs/2604.05350 |