多阶段验证导向框架用于缓解多模态RAG中的幻觉
Multi-Stage Verification-Centric Framework for Mitigating Hallucination in Multi-Modal RAG
AI总结：
本文提出了一种多阶段验证导向框架，通过优先考虑事实准确性和真实性来缓解多模态RAG中的幻觉问题，并在KDD Cup 2025中取得第三名。
摘要：
本文介绍了团队CRUISE为KDD Cup 2025元综合RAG基准测试（多模态、多轮挑战）开发的技术解决方案。该挑战旨在解决现代视觉语言模型（VLMs）的一个关键限制：它们容易产生幻觉，尤其是在面对自拍图像、长尾实体和复杂多跳问题时。这一问题在现实应用中尤为突出，因为用户会提出需要高事实准确性跨多样模态的事实查询。为此，我们提出了一种稳健的多阶段框架，优先考虑事实准确性和真实性而非完整性。我们的解决方案整合了轻量级查询路由器以提高效率，查询感知的检索和摘要管道，双路径生成以及事后验证。这种保守策略旨在最小化幻觉，因为幻觉在竞赛评分指标中会造成严重惩罚。我们的方法在任务1中获得了第三名，证明了在复杂多模态RAG系统中优先考虑答案可靠性是有效的。我们的实现可在https://github.com/Breezelled/KDD-Cup-2025-Meta-CRAG-MM上找到。
英文摘要：
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 .
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
