融合多种检索方法与大模型重排，提升模糊记忆查询的召回效果。
DS@GT at TREC TOT 2025: Bridging Vague Recollection with Fusion Retrieval and Learned Reranking
- 采用混合检索融合LLM、BM25和BGE-M3三类方法，提升信息覆盖。
- 通过24个主题分区的密集检索，增强相关性定位精度。
- 结合大模型重排实现0.66召回率，适合应对记忆模糊的搜索任务。
我们构建了一个两阶段检索系统，用于解决TREC Tip-of-the-Tongue（ToT）任务。第一阶段采用混合检索，融合基于大模型的检索、稀疏检索（BM25）和稠密检索（BGE-M3）方法，并引入主题感知的多索引稠密检索，将维基百科语料按24个主题领域进行划分。第二阶段评估了训练的LambdaMART重排器与基于大模型的重排策略。为支持模型训练，使用大模型生成了5000条合成的ToT查询。最佳系统在测试集上达到0.66的召回率和0.41的NDCG@1000，通过融合混合检索与Gemini-2.5-flash重排实现，验证了融合检索的有效性。
原文摘要 · Abstract (English)
We develop a two-stage retrieval system that combines multiple complementary retrieval methods with a learned reranker and LLM-based reranking, to address the TREC Tip-of-the-Tongue (ToT) task. In the first stage, we employ hybrid retrieval that merges LLM-based retrieval, sparse (BM25), and dense (BGE-M3) retrieval methods. We also introduce topic-aware multi-index dense retrieval that partitions the Wikipedia corpus into 24 topical domains. In the second stage, we evaluate both a trained LambdaMART reranker and LLM-based reranking. To support model training, we generate 5000 synthetic ToT queries using LLMs. Our best system achieves recall of 0.66 and NDCG@1000 of 0.41 on the test set by combining hybrid retrieval with Gemini-2.5-flash reranking, demonstrating the effectiveness of fusion retrieval.
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。