@inproceedings{rosenthal-etal-2026-mtrag,
    title = "{MTRAG}-{UN}: A Benchmark for Open Challenges in Multi-Turn {RAG} Conversations",
    author = "Rosenthal, Sara  and
      Katsis, Yannis  and
      Shah, Vraj  and
      He, Lihong  and
      Popa, Lucian  and
      Danilevsky, Marina",
    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.503/",
    pages = "10363--10369",
    ISBN = "979-8-89176-395-1",
    abstract = "We present MTRAG-UN, a benchmark for exploring open challenges in multi-turn retrieval augment generation, a popular use of large language models. We release a benchmark of 666 tasks from 666 conversations containing over 2,800 conversation turns across 6 domains with accompanying corpora. Our experiments show that retrieval and generation models continue to struggle on conversations with UNanswerable, UNderspecified, and NONstandalone questions and UNclear responses. Our benchmark is available at https://github.com/IBM/mt-rag-benchmark"
}