Multi-Stage Verification-Centric Framework for Mitigating Hallucination in Multi-Modal RAG
This addresses the critical limitation of hallucination in multi-modal RAG systems for real-world fact-seeking queries, though it is incremental as it builds on existing verification and retrieval methods.
The paper tackled the problem of hallucination in Vision Language Models when handling egocentric imagery, long-tail entities, and complex multi-hop questions, achieving 3rd place in the KDD Cup 2025 Meta CRAG-MM challenge by prioritizing factual accuracy over completeness.
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 .