IIMAS-RAG at SemEval-2026 Task 8: Hybrid Sparse-Dense Retrieval and Answerability-Conditioned Generation for Multi-Turn RAG
TL;DR
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).
Abstract
This paper presents the IIMAS-RAG system submitted to SemEval-2026 Task 8, which evaluates multi-turn retrieval-augmented generation (RAG) conversations. Our system is a modular pipeline composed of three stages: (1) LLM-based query rewriting to transform conversational history into standalone queries, (2) hybrid sparse–dense retrieval combining SPLADE and Voyage-3-large via Reciprocal Rank Fusion (RRF), and (3) answerability-conditioned generation using GPT-4.1. In Sub-task A (Retrieval), our system ranked 4th out of 38 teams (nDCG@5 = 0.5445), demonstrating the robustness of the hybrid retrieval strategy in specialized domains. On Subtask C (Full RAG), we ranked 13th out of 29 teams (composite = 0.5397). Ablation experiments show that LLM-based query rewriting is the main driver of retrieval performance, yielding a +16.3% relative gain in nDCG@10 over the hybrid baseline without rewriting, while domain-specific prompt variants provide only localized gains on specialized corpora. Generative performance remains sensitive to low-context and partially answerable turns, where the user query lacks sufficient grounding information and the model struggles to either abstain or provide a properly qualified partial answer, explaining the performance gap between retrieval and final synthesis. Our code is available at https://github.com/PLN-disca-iimas/ mtrag_semeval2026 .