GenAIus at SemEval-2026 Task 8: Beyond Retrieval with Relevance-Aware RAG for Faithful Multi-Turn Generation
Year: 2026
Type: conference-paper
Abstract: This paper describes our submission to SemEval-2026 Task 8 on multi-turn retrievalaugmented generation (RAG).We propose a hybrid multi-stage pipeline that combines high-recall lexical retrieval, dual-embedding dense re-ranking with reciprocal rank fusion, LLM-based relevance judging, and strictly constrained evidence-grounded generation.Our design emphasizes robustness and faithfulness across the full retrieval-to-generation pipeline.Our results suggest that relevance-aware filtering and constrained generation are important for improving faithfulness and overall RAG performance.
Authors: Suveyda Yeniterzi, Reyyan Yeniterzi
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166850733