用单次大模型重写模糊查询，显著提升找熟人熟物的检索效果。
Single-Turn LLM Reformulation Powered Multi-Stage Hybrid Re-Ranking for Tip-of-the-Tongue Known-Item Retrieval
- 仅用一次80亿参数大模型重写查询，无需微调
- 召回率提升20.61%，多项指标改善超29%
- 适合需要低成本提升检索效果的研究与应用
从模糊描述中检索已知项目（即“舌尖现象”检索）仍是重大挑战。我们提出仅通过一次通用80亿参数大模型调用进行查询重写，弥合模糊查询与具体信息需求之间的差距。该方法在标准伪相关反馈因初始召回率低而失效时尤为有效。关键在于，所用大模型未针对舌尖现象或特定领域微调，表明性能提升源于提示策略而非模型定制。重写后的查询输入多阶段流水线：稀疏检索（BM25）、稠密/后期交互重排（Contriever、E5-large-v2、ColBERTv2）、monoT5交叉编码，以及列表级重排（Qwen 2.5 72B）。在2025年TREC-ToT数据集上的实验显示，原始查询表现不佳，但轻量级预重写使召回率提升20.61%；后续重排使nDCG@10提升33.88%，MRR提升29.92%，MAP@10提升29.98%，以低成本释放下游排序器潜力。代码与数据：https://github.com/debayan1405/TREC-TOT-2025
原文摘要 · Abstract (English)
Retrieving known items from vague descriptions, Tip-of-the-Tongue (ToT) retrieval, remains a significant challenge. We propose using a single call to a generic 8B-parameter LLM for query reformulation, bridging the gap between ill-formed ToT queries and specific information needs. This method is particularly effective where standard Pseudo-Relevance Feedback fails due to poor initial recall. Crucially, our LLM is not fine-tuned for ToT or specific domains, demonstrating that gains stem from our prompting strategy rather than model specialization. Rewritten queries feed a multi-stage pipeline: sparse retrieval (BM25), dense/late-interaction reranking (Contriever, E5-large-v2, ColBERTv2), monoT5 cross-encoding, and list-wise reranking (Qwen 2.5 72B). Experiments on 2025 TREC-ToT datasets show that while raw queries yield poor performance, our lightweight pre-retrieval transformation improves Recall by 20.61%. Subsequent reranking improves nDCG@10 by 33.88%, MRR by 29.92%, and MAP@10 by 29.98%, offering a cost-effective intervention that unlocks the potential of downstream rankers. Code and data: https://github.com/debayan1405/TREC-TOT-2025
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。