Year: 2025
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Authors: Jin, Can, Peng, Hongwu, Zhang, Anxiang, Chen, Nuo, Zhao, Jiahui, Xie, Xi, Li, Kuangzheng, Feng, Shuya, Zhong, Kai, Ding, Caiwen, Metaxas, Dimitris N.
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4407124017