分层检索提升多轮对话生成质量，母文档保上下文，子段落精准找信息。
H-RAG at SemEval-2026 Task 8: Hierarchical Parent-Child Retrieval for Multi-Turn RAG Conversations
- 用父子分层结构，子段精检、母文保上下文，解决多轮对话信息碎片化。
- 任务A检索nDCG@5达0.4271，任务C综合得分0.3241，母级聚合显著提准。
- 适合做多轮问答、需要可靠证据链的生成系统开发者参考。
我们提出H-RAG，提交至SemEval-2026 Task 8（MTRAGEval），同时应对任务A（检索）和任务C（基于检索文本的生成）。任务A评估独立检索质量，任务C则评估多轮对话中端到端检索增强生成性能，要求答案准确且有据可依。本方法采用分层父子检索架构：将文档切分为重叠句级子块用于细粒度检索，同时保留完整文档作为父单元以提供连贯上下文。检索融合混合密集-稀疏搜索、可调权重与嵌入相似性重排序，作用于子块。检索结果在父层级聚合后输入指令微调语言模型生成回答。H-RAG在任务A上取得nDCG@5为0.4271，在任务C上获得调和均值0.3241（RB_agg: 0.2488, RL_F: 0.2703, RB_llm: 0.6508），凸显检索配置与父级聚合对多轮RAG表现的关键作用。
原文摘要 · Abstract (English)
We present H-RAG, our submission to SemEval-2026 Task 8 (MTRAGEval), addressing both Task A (Retrieval) and Task C (Generation with Retrieved Passages). Task A evaluates standalone retrieval quality, while Task C assesses end-to-end retrieval-augmented generation (RAG) in multi-turn conversational settings, requiring both accurate answer generation and faithful grounding in retrieved evidence. Our approach implements a hierarchical parent-child RAG pipeline that separates fine-grained child-level retrieval from parent-level context reconstruction during generation. Documents are segmented into overlapping sentence-based child chunks, while full documents are preserved as parent units to provide coherent context. Retrieval combines hybrid dense-sparse search, tunable weighting, and embedding-based similarity rescoring over child chunks. Retrieved evidence is aggregated at the parent level and supplied to an instruction-tuned language model for response generation. H-RAG achieves an nDCG@5 score of 0.4271 on Task A and a harmonic mean score of 0.3241 on Task C (RB_agg: 0.2488, RL_F: 0.2703, RB_llm: 0.6508), underscoring the importance of retrieval configuration and parent-level aggregation in multi-turn RAG performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。