{"ID":2890270,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.18857","arxiv_id":"2507.18857","title":"PrismRAG: Boosting RAG Factuality with Distractor Resilience and Strategized Reasoning","abstract":"Retrieval-augmented generation (RAG) often falls short when retrieved context includes confusing semi-relevant passages, or when answering questions require deep contextual understanding and reasoning. We propose an efficient fine-tuning framework, called PrismRAG, that (i) trains the model with distractor-aware QA pairs mixing gold evidence with subtle distractor passages, and (ii) instills reasoning-centric habits that make the LLM plan, rationalize, and synthesize without relying on extensive human engineered instructions. Evaluated across 12 open-book RAG QA benchmarks spanning diverse application domains and scenarios, PrismRAG improves average factuality by 5.4%, outperforming state-of-the-art solutions.","short_abstract":"Retrieval-augmented generation (RAG) often falls short when retrieved context includes confusing semi-relevant passages, or when answering questions require deep contextual understanding and reasoning. We propose an efficient fine-tuning framework, called PrismRAG, that (i) trains the model with distractor-aware QA pai...","url_abs":"https://arxiv.org/abs/2507.18857","url_pdf":"https://arxiv.org/pdf/2507.18857v1","authors":"[\"Mohammad Kachuee\",\"Teja Gollapudi\",\"Minseok Kim\",\"Yin Huang\",\"Kai Sun\",\"Xiao Yang\",\"Jiaqi Wang\",\"Nirav Shah\",\"Yue Liu\",\"Aaron Colak\",\"Anuj Kumar\",\"Wen-tau Yih\",\"Xin Luna Dong\"]","published":"2025-07-25T00:15:31Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.LG\"]","methods":"[\"RAG\",\"Large Language Model\"]","has_code":false}