SlugRAG at SemEval-2026 Task 8: Domain-Specific Fine-Tuning and Model Scaling for Multi-Turn RAG Retrieval
Year: 2026
Type: conference-paper
Abstract: Multi-Turn Retrieval-Augmented Generation (MT-RAG) requires resolving contextdependent ambiguities across conversational turns.We present a systematic evaluation of dense retrieval optimization for the MTRAGEval benchmark (Task 8, Subtask A: Retrieval Only), investigating training-time strategies and inference-time query reformulation across four diverse English-language domains: CLAPNQ (legal/patent), FIQA (financial), GOVT (government documents), and CLOUD (cloud computing).Our experiments demonstrate that domain-specific fine-tuning yields the most substantial gains, with our best CLAPNQ model achieving Recall@10 of 0.6016 and nDCG@10 of 0.4981-representing 58.3% and 66.0% improvements over the pre-trained BGE baseline.Domain-specific models average 44.3% improvement in Recall@10 and 47.8% in nDCG@10 across all domains.Additionally, fine-tuning larger embedding models (BGE-large) achieves the best overall performance (nDCG@10: 0.5101, Recall@10: 0.6221), highlighting the complementary impact of model capacity and domain adaptation.
Authors: Pratibha Revankar, Jihye Kim, Umit Azirakhmet
Institution: University of California, Santa Cruz
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166859295