Open access
2026
IIMAS-RAG at SemEval-2026 Task 8: Hybrid Sparse-Dense Retrieval and Answerability-Conditioned Generation for Multi-Turn RAG
This paper presents the IIMAS-RAG system, which evaluates multi-turn retrieval-augmented generation (RAG) conversations, a modular pipeline composed of LLM-based query rewriting to transform conversational history into standalone queries, and hybrid sparse–dense retrieval combining SPLADE and Voyage-3-large via Reciprocal Rank Fusion (RRF).
Vania Raya-Rios, Helena Gómez-Adorno, Leon Hecht et al.
· SemEval@ACL · 1 citation