Rank4Gen: RAG-Preference-Aligned Document Set Selection and Ranking
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917324004524032 |
|---|---|
| author | Fan, Yongqi Chu, Yuxiang Xia, Zhentao Chen, Xiaoyang Liu, Jie Liang, Haijin Ma, Jin He, Ben Sun, Yingfei Ye, Dezhi Ruan, Tong |
| author_facet | Fan, Yongqi Chu, Yuxiang Xia, Zhentao Chen, Xiaoyang Liu, Jie Liang, Haijin Ma, Jin He, Ben Sun, Yingfei Ye, Dezhi Ruan, Tong |
| contents | In the RAG paradigm, the information retrieval module provides context for generators by retrieving and ranking multiple documents to support the aggregation of evidence. However, existing ranking models are primarily optimized for query--document relevance, which often misaligns with generators' preferences for evidence selection and citation, limiting their impact on response quality. Moreover, most approaches do not account for preference differences across generators, resulting in unstable cross-generator performance. We propose \textbf{Rank4Gen}, a generator-aware ranker for RAG that targets the goal of \emph{Ranking for Generators}. Rank4Gen introduces two key preference modeling strategies: (1) \textbf{From Ranking Relevance to Response Quality}, which optimizes ranking with respect to downstream response quality rather than query--document relevance; and (2) \textbf{Generator-Specific Preference Modeling}, which conditions a single ranker on different generators to capture their distinct ranking preferences. To enable such modeling, we construct \textbf{PRISM}, a dataset built from multiple open-source corpora and diverse downstream generators. Experiments on five challenging and recent RAG benchmarks demonstrate that Rank4Gen achieves strong and competitive performance for complex evidence composition in RAG. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_11273 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Rank4Gen: RAG-Preference-Aligned Document Set Selection and Ranking Fan, Yongqi Chu, Yuxiang Xia, Zhentao Chen, Xiaoyang Liu, Jie Liang, Haijin Ma, Jin He, Ben Sun, Yingfei Ye, Dezhi Ruan, Tong Information Retrieval In the RAG paradigm, the information retrieval module provides context for generators by retrieving and ranking multiple documents to support the aggregation of evidence. However, existing ranking models are primarily optimized for query--document relevance, which often misaligns with generators' preferences for evidence selection and citation, limiting their impact on response quality. Moreover, most approaches do not account for preference differences across generators, resulting in unstable cross-generator performance. We propose \textbf{Rank4Gen}, a generator-aware ranker for RAG that targets the goal of \emph{Ranking for Generators}. Rank4Gen introduces two key preference modeling strategies: (1) \textbf{From Ranking Relevance to Response Quality}, which optimizes ranking with respect to downstream response quality rather than query--document relevance; and (2) \textbf{Generator-Specific Preference Modeling}, which conditions a single ranker on different generators to capture their distinct ranking preferences. To enable such modeling, we construct \textbf{PRISM}, a dataset built from multiple open-source corpora and diverse downstream generators. Experiments on five challenging and recent RAG benchmarks demonstrate that Rank4Gen achieves strong and competitive performance for complex evidence composition in RAG. |
| title | Rank4Gen: RAG-Preference-Aligned Document Set Selection and Ranking |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2601.11273 |