What Should I Cite? A RAG Benchmark for Academic Citation Prediction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917223075938304 |
|---|---|
| author | Zheng, Leqi Zhang, Jiajun Chen, Canzhi Wang, Chaokun Li, Hongwei Li, Yuying Mao, Yaoxin Yan, Shannan Song, Zixin Feng, Zhiyuan Kang, Zhaolu Chen, Zirong Zhang, Hang Liu, Qiang Wang, Liang Liu, Ziyang |
| author_facet | Zheng, Leqi Zhang, Jiajun Chen, Canzhi Wang, Chaokun Li, Hongwei Li, Yuying Mao, Yaoxin Yan, Shannan Song, Zixin Feng, Zhiyuan Kang, Zhaolu Chen, Zirong Zhang, Hang Liu, Qiang Wang, Liang Liu, Ziyang |
| contents | With the rapid growth of Web-based academic publications, more and more papers are being published annually, making it increasingly difficult to find relevant prior work. Citation prediction aims to automatically suggest appropriate references, helping scholars navigate the expanding scientific literature. Here we present \textbf{CiteRAG}, the first comprehensive retrieval-augmented generation (RAG)-integrated benchmark for evaluating large language models on academic citation prediction, featuring a multi-level retrieval strategy, specialized retrievers, and generators. Our benchmark makes four core contributions: (1) We establish two instances of the citation prediction task with different granularity. Task 1 focuses on coarse-grained list-specific citation prediction, while Task 2 targets fine-grained position-specific citation prediction. To enhance these two tasks, we build a dataset containing 7,267 instances for Task 1 and 8,541 instances for Task 2, enabling comprehensive evaluation of both retrieval and generation. (2) We construct a three-level large-scale corpus with 554k papers spanning many major subfields, using an incremental pipeline. (3) We propose a multi-level hybrid RAG approach for citation prediction, fine-tuning embedding models with contrastive learning to capture complex citation relationships, paired with specialized generation models. (4) We conduct extensive experiments across state-of-the-art language models, including closed-source APIs, open-source models, and our fine-tuned generators, demonstrating the effectiveness of our framework. Our open-source toolkit enables reproducible evaluation and focuses on academic literature, providing the first comprehensive evaluation framework for citation prediction and serving as a methodological template for other scientific domains. Our source code and data are released at https://github.com/LQgdwind/CiteRAG. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_14949 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | What Should I Cite? A RAG Benchmark for Academic Citation Prediction Zheng, Leqi Zhang, Jiajun Chen, Canzhi Wang, Chaokun Li, Hongwei Li, Yuying Mao, Yaoxin Yan, Shannan Song, Zixin Feng, Zhiyuan Kang, Zhaolu Chen, Zirong Zhang, Hang Liu, Qiang Wang, Liang Liu, Ziyang Information Retrieval With the rapid growth of Web-based academic publications, more and more papers are being published annually, making it increasingly difficult to find relevant prior work. Citation prediction aims to automatically suggest appropriate references, helping scholars navigate the expanding scientific literature. Here we present \textbf{CiteRAG}, the first comprehensive retrieval-augmented generation (RAG)-integrated benchmark for evaluating large language models on academic citation prediction, featuring a multi-level retrieval strategy, specialized retrievers, and generators. Our benchmark makes four core contributions: (1) We establish two instances of the citation prediction task with different granularity. Task 1 focuses on coarse-grained list-specific citation prediction, while Task 2 targets fine-grained position-specific citation prediction. To enhance these two tasks, we build a dataset containing 7,267 instances for Task 1 and 8,541 instances for Task 2, enabling comprehensive evaluation of both retrieval and generation. (2) We construct a three-level large-scale corpus with 554k papers spanning many major subfields, using an incremental pipeline. (3) We propose a multi-level hybrid RAG approach for citation prediction, fine-tuning embedding models with contrastive learning to capture complex citation relationships, paired with specialized generation models. (4) We conduct extensive experiments across state-of-the-art language models, including closed-source APIs, open-source models, and our fine-tuned generators, demonstrating the effectiveness of our framework. Our open-source toolkit enables reproducible evaluation and focuses on academic literature, providing the first comprehensive evaluation framework for citation prediction and serving as a methodological template for other scientific domains. Our source code and data are released at https://github.com/LQgdwind/CiteRAG. |
| title | What Should I Cite? A RAG Benchmark for Academic Citation Prediction |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2601.14949 |