QDRAG框架用查询分解提升多模态RAG引用忠实度
Faithful in Steps: Improving Generalization and Citation in RAG via Query Decomposition
做 RAG 引用质量的同学可以看看这篇。它把问题拆成子问题再加重排剪枝，专门解决多跳问答里引用乱标、实体识别不到的老毛病，四个多模态 QA 基准上连 Gemini-Pro 都被比下去了。
arXiv 论文提出 QDRAG 框架，针对现有可归因 RAG（RAGQ）在多跳推理和多模态理解场景下的过引用、隐式实体识别失败和泛化差等问题给出改进方案。框架先将输入问题拆解为原子子问题以识别隐式实体，再用重排序器剪除上下文干扰项，从而消除下游的过引用现象。
为支持查询分解，作者提出 QD-C 和 QD-R 两种零样本方法，分别基于上下文知识和检索奖励引导 QD 多模态大模型完成问题拆解。一个有趣的发现是：在 QD 任务上微调比直接在下游 RAGQ 任务上微调具有更好的泛化能力。
实验在四个多模态 QA 基准上进行，QDRAG 在域内和域外测试中均超过所有基线，甚至超过 Gemini-Pro，显著改善了答案 grounding 和引用生成的忠实度。
Faithful in Steps: Improving Generalization and Citation in RAG via Query Decomposition
Retrieval-augment generation is a prevalent strategy to mitigate hallucinations of LLMs. The attributable RAG (RAGQ) generates quotes for its answers. The quotes indicate which input contexts support the RAG to derive the answers, enhancing the answer's verifiability and trustworthiness. However, existing RAGQs exhibit significant degradation when dealing with questions that require multi-hop reasoning and multi-modal understanding, suffering from over-citation, implicit entity identification failure, and poor generalization. In this paper, we propose a novel RAGQ framework, namely QDRAG. QDRAG breaks down the input question into atomic subquestions to identify the implicit entities. Then, the reranker prunes context distractors to eliminate the downstream over-citation. To facilitate query decomposition, we propose two zero-shot approaches: QD-C and QD-R, which guide the QD MLLM to decompose the question based on context knowledge and retrieval rewards, respectively. One interesting finding is that finetuning on the QD task shows better generalizability compared to directly finetuning on the downstream RAGQ task. Experiments on four multi-modal QA benchmarks demonstrate QDRAG's efficacy in grounding answers and generating faithful citations. The framework significantly outperforms all the baselines on both in-domain and out-of-domain tests, even surpassing Gemini-Pro.
本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中，该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：RAG、QDRAG、Gemini-Pro、多模态，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明：本文原始线索采编自「arXiv cs.AI」（@Yue Liu, Zhongying Ru, Shimin Di, Jipeng Zhang, Ruiyuan Zhang, Xiaofang Zhou），经 AITOP 多维评分管线结构化提炼。
