LoRA-enhanced query rewriting in hybrid retrieval for multi-turn dialogue benchmarks

We describe our system for SemEval-2026 Task 8 (MTRAGEval), participating in Task A (Retrieval) across four English-language domains. Our approach employs a three-stage pipeline: (1) query rewriting via a LoRA-fine-tuned Qwen 2.5 7B model that transforms context-dependent follow-up questions into standalone queries, (2) hybrid BM25 and dense retrieval combined through Reciprocal Rank Fusion, and (3) cross-encoder reranking with BGE-reranker-v2-m3. On the official test set, the system achieves nDCG@5 of 0.531, ranking 8th out of 38 participating systems and 10.7\% above the organizer baseline. D

Research goal: How does the integration of LoRA-fine-tuned query rewriting with hybrid DPR and BM25 retrieval affect nDCG scores on multi-turn dialogue benchmarks compared to standalone dense retrieval methods?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.1/10.