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.
@article{arxiv.2507.18857,
title = {PrismRAG: Boosting RAG Factuality with Distractor Resilience and Strategized Reasoning},
author = {Mohammad Kachuee and Teja Gollapudi and Minseok Kim and Yin Huang and Kai Sun and Xiao Yang and Jiaqi Wang and Nirav Shah and Yue Liu and Aaron Colak and Anuj Kumar and Wen-tau Yih and Xin Luna Dong},
journal= {arXiv preprint arXiv:2507.18857},
year = {2025}
}