通过聚类筛选相关文本，提升大模型问答的准确与可信度。
TopClustRAG at SIGIR 2025 LiveRAG Challenge
- 混合稀疏与稠密检索，再用K-Means聚类分组相似段落。
- 聚类内选代表性片段生成答案，综合后得分位列第二（忠实度）。
- 适合追求高可信度问答的工程应用或系统研发者。
我们提出TopClustRAG，一个为LiveRAG Challenge设计的检索增强生成系统，用于在大规模网络语料上进行端到端问答。该系统结合稀疏与稠密索引的混合检索策略，随后采用K-Means聚类将语义相似的文本分组。从每个聚类中选取代表性段落，构建特定于聚类的提示词输入大语言模型（LLM），生成中间答案。这些答案经过过滤、重排序后合成最终响应。该多阶段流程提升了答案的多样性、相关性及对检索证据的忠实度。在FineWeb Sample-10BT数据集上评估，TopClustRAG在官方排行榜上以忠实度第二、正确性第七的成绩表现优异，验证了基于聚类的上下文过滤与提示聚合在大规模RAG系统中的有效性。
原文摘要 · Abstract (English)
We present TopClustRAG, a retrieval-augmented generation (RAG) system developed for the LiveRAG Challenge, which evaluates end-to-end question answering over large-scale web corpora. Our system employs a hybrid retrieval strategy combining sparse and dense indices, followed by K-Means clustering to group semantically similar passages. Representative passages from each cluster are used to construct cluster-specific prompts for a large language model (LLM), generating intermediate answers that are filtered, reranked, and finally synthesized into a single, comprehensive response. This multi-stage pipeline enhances answer diversity, relevance, and faithfulness to retrieved evidence. Evaluated on the FineWeb Sample-10BT dataset, TopClustRAG ranked 2nd in faithfulness and 7th in correctness on the official leaderboard, demonstrating the effectiveness of clustering-based context filtering and prompt aggregation in large-scale RAG systems.
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。