用大模型分角色协作重排，提升搜索结果相关性。
RankFlow: A Multi-Role Collaborative Reranking Workflow Utilizing Large Language Models
- 大模型分四角色：重写查询、生成伪答案、摘要段落、综合重排。
- 在TREC-DL等三大数据集上表现优于现有方法。
- 适合需要高精度检索的场景，如智能客服与科研问答。
在信息检索系统中，重排通过根据候选段落与查询的相关性进行排序起着关键作用。该过程需要对与查询相关的段落差异有细致理解。本文提出RankFlow，一种利用大语言模型和角色专业化实现多角色协作重排的工作流。RankFlow让大模型承担四个不同角色：查询重写者、伪回答者、段落摘要者和重排者。这种协同机制使RankFlow能够准确理解查询、利用大模型的广泛预训练知识、将段落提炼为简洁版本，并以全面方式评估段落，从而显著提升重排效果。实验结果显示，RankFlow在TREC-DL、BEIR和NovelEval等广泛认可的信息检索基准上均优于现有领先方法。此外，我们还分析了各角色在RankFlow中的独立贡献。
原文摘要 · Abstract (English)
In an Information Retrieval (IR) system, reranking plays a critical role by sorting candidate passages according to their relevance to a specific query. This process demands a nuanced understanding of the variations among passages linked to the query. In this work, we introduce RankFlow, a multi-role reranking workflow that leverages the capabilities of Large Language Models (LLMs) and role specializations to improve reranking performance. RankFlow enlists LLMs to fulfill four distinct roles: the query Rewriter, the pseudo Answerer, the passage Summarizer, and the Reranker. This orchestrated approach enables RankFlow to: (1) accurately interpret queries, (2) draw upon LLMs' extensive pre-existing knowledge, (3) distill passages into concise versions, and (4) assess passages in a comprehensive manner, resulting in notably better reranking results. Our experimental results reveal that RankFlow outperforms existing leading approaches on widely recognized IR benchmarks, such as TREC-DL, BEIR, and NovelEval. Additionally, we investigate the individual contributions of each role in RankFlow.
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。