RankFlow: A Multi-Role Collaborative Reranking Workflow Utilizing Large Language Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910136779407360 |
|---|---|
| author | Jin, Can Peng, Hongwu Zhang, Anxiang Chen, Nuo Zhao, Jiahui Xie, Xi Li, Kuangzheng Feng, Shuya Zhong, Kai Ding, Caiwen Metaxas, Dimitris N. |
| author_facet | Jin, Can Peng, Hongwu Zhang, Anxiang Chen, Nuo Zhao, Jiahui Xie, Xi Li, Kuangzheng Feng, Shuya Zhong, Kai Ding, Caiwen Metaxas, Dimitris N. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_00709 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RankFlow: A Multi-Role Collaborative Reranking Workflow Utilizing Large Language Models Jin, Can Peng, Hongwu Zhang, Anxiang Chen, Nuo Zhao, Jiahui Xie, Xi Li, Kuangzheng Feng, Shuya Zhong, Kai Ding, Caiwen Metaxas, Dimitris N. Information Retrieval 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. |
| title | RankFlow: A Multi-Role Collaborative Reranking Workflow Utilizing Large Language Models |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2502.00709 |