MTRAG-UN: A Benchmark for Open Challenges in Multi-Turn RAG Conversations (2026 · 27 citations)
MTRAG-UN is a new benchmark from IBM Research. It targets cases in multi-turn retrieval-augmented generation (RAG) where a single question-answer exchange is not enough for the user. It extends the earlier MTRAG benchmark with four stress cases:
SemEval-2026 Task 8: MTRAGEval: Evaluating Multi-Turn RAG Conversations (2026 · 26 citations)
This shared task evaluates retrieval-augmented generation in multi-turn dialogue. In that setting, follow-up questions often depend on earlier turns, cannot be answered from the corpus, or are ambiguous. The organizers split the pipeline into three subtasks: retrieval only (A), answer generation from gold passages…

Co-authors here

3 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 53 times (of the 149,439 papers whose bibliographies we read); 14 citing papers with a page here →.

Updated 31 October 2026