{"ID":2889862,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.20136","arxiv_id":"2507.20136","title":"Multi-Stage Verification-Centric Framework for Mitigating Hallucination in Multi-Modal RAG","abstract":"This paper presents the technical solution developed by team CRUISE for the KDD Cup 2025 Meta Comprehensive RAG Benchmark for Multi-modal, Multi-turn (CRAG-MM) challenge. The challenge aims to address a critical limitation of modern Vision Language Models (VLMs): their propensity to hallucinate, especially when faced with egocentric imagery, long-tail entities, and complex, multi-hop questions. This issue is particularly problematic in real-world applications where users pose fact-seeking queries that demand high factual accuracy across diverse modalities. To tackle this, we propose a robust, multi-stage framework that prioritizes factual accuracy and truthfulness over completeness. Our solution integrates a lightweight query router for efficiency, a query-aware retrieval and summarization pipeline, a dual-pathways generation and a post-hoc verification. This conservative strategy is designed to minimize hallucinations, which incur a severe penalty in the competition's scoring metric. Our approach achieved 3rd place in Task 1, demonstrating the effectiveness of prioritizing answer reliability in complex multi-modal RAG systems. Our implementation is available at https://github.com/Breezelled/KDD-Cup-2025-Meta-CRAG-MM .","short_abstract":"This paper presents the technical solution developed by team CRUISE for the KDD Cup 2025 Meta Comprehensive RAG Benchmark for Multi-modal, Multi-turn (CRAG-MM) challenge. The challenge aims to address a critical limitation of modern Vision Language Models (VLMs): their propensity to hallucinate, especially when faced w...","url_abs":"https://arxiv.org/abs/2507.20136","url_pdf":"https://arxiv.org/pdf/2507.20136v2","authors":"[\"Baiyu Chen\",\"Wilson Wongso\",\"Xiaoqian Hu\",\"Yue Tan\",\"Flora Salim\"]","published":"2025-07-27T05:45:45Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.IR\"]","methods":"[\"Language Model\"]","has_code":false,"code_links":[{"ID":611697,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2889862,"paper_url":"https://arxiv.org/abs/2507.20136","paper_title":"Multi-Stage Verification-Centric Framework for Mitigating Hallucination in Multi-Modal RAG","repo_url":"https://github.com/Breezelled/KDD-Cup-2025-Meta-CRAG-MM","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}