A multi-turn RAG system combines learned sparse retrieval with LLM-conditioned rewriting, listwise reranking, and generation to handle conversational QA and unanswerable queries across four domains.
From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective , year =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
uva-irlab-conv at SemEval-2026 Task 8: Multi-Turn RAG with Learned Sparse Retrieval and Listwise Reranking
A multi-turn RAG system combines learned sparse retrieval with LLM-conditioned rewriting, listwise reranking, and generation to handle conversational QA and unanswerable queries across four domains.