MTRAG-UN: A Benchmark for Open Challenges in Multi-Turn RAG Conversations

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Rosenthal, Sara, Katsis, Yannis, Shah, Vraj, He, Lihong, Popa, Lucian, Danilevsky, Marina
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908854708600832
author Rosenthal, Sara
Katsis, Yannis
Shah, Vraj
He, Lihong
Popa, Lucian
Danilevsky, Marina
author_facet Rosenthal, Sara
Katsis, Yannis
Shah, Vraj
He, Lihong
Popa, Lucian
Danilevsky, Marina
contents We present MTRAG-UN, a benchmark for exploring open challenges in multi-turn retrieval augmented generation, a popular use of large language models. We release a benchmark of 666 tasks 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
format Preprint
id arxiv_https___arxiv_org_abs_2602_23184
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MTRAG-UN: A Benchmark for Open Challenges in Multi-Turn RAG Conversations
Rosenthal, Sara
Katsis, Yannis
Shah, Vraj
He, Lihong
Popa, Lucian
Danilevsky, Marina
Computation and Language
We present MTRAG-UN, a benchmark for exploring open challenges in multi-turn retrieval augmented generation, a popular use of large language models. We release a benchmark of 666 tasks 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
title MTRAG-UN: A Benchmark for Open Challenges in Multi-Turn RAG Conversations
topic Computation and Language
url https://arxiv.org/abs/2602.23184