GraphER: An Efficient Graph-Based Enrichment and Reranking Method for Retrieval-Augmented Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908914349506560 |
|---|---|
| author | Miao, Ruizhong Wang, Yuying Wang, Rongguang Li, Chenyang Sheng, Tao Ravi, Sujith Roth, Dan |
| author_facet | Miao, Ruizhong Wang, Yuying Wang, Rongguang Li, Chenyang Sheng, Tao Ravi, Sujith Roth, Dan |
| contents | Semantic search in retrieval-augmented generation (RAG) systems is often insufficient for complex information needs, particularly when relevant evidence is scattered across multiple sources. Prior approaches to this problem include agentic retrieval strategies, which expand the semantic search space by generating additional queries. However, these methods do not fully leverage the organizational structure of the data and instead rely on iterative exploration, which can lead to inefficient retrieval. Another class of approaches employs knowledge graphs to model non-semantic relationships through graph edges. Although effective in capturing richer proximities, such methods incur significant maintenance costs and are often incompatible with the vector stores used in most production systems. To address these limitations, we propose GraphER, a graph-based enrichment and reranking method that captures multiple forms of proximity beyond semantic similarity. GraphER independently enriches data objects during offline indexing and performs graph-based reranking over candidate objects at query time. This design does not require a knowledge graph, allowing GraphER to integrate seamlessly with standard vector stores. In addition, GraphER is retriever-agnostic and introduces negligible latency overhead. Experiments on multiple retrieval benchmarks demonstrate the effectiveness of the proposed approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_24925 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GraphER: An Efficient Graph-Based Enrichment and Reranking Method for Retrieval-Augmented Generation Miao, Ruizhong Wang, Yuying Wang, Rongguang Li, Chenyang Sheng, Tao Ravi, Sujith Roth, Dan Machine Learning Computation and Language Information Retrieval Semantic search in retrieval-augmented generation (RAG) systems is often insufficient for complex information needs, particularly when relevant evidence is scattered across multiple sources. Prior approaches to this problem include agentic retrieval strategies, which expand the semantic search space by generating additional queries. However, these methods do not fully leverage the organizational structure of the data and instead rely on iterative exploration, which can lead to inefficient retrieval. Another class of approaches employs knowledge graphs to model non-semantic relationships through graph edges. Although effective in capturing richer proximities, such methods incur significant maintenance costs and are often incompatible with the vector stores used in most production systems. To address these limitations, we propose GraphER, a graph-based enrichment and reranking method that captures multiple forms of proximity beyond semantic similarity. GraphER independently enriches data objects during offline indexing and performs graph-based reranking over candidate objects at query time. This design does not require a knowledge graph, allowing GraphER to integrate seamlessly with standard vector stores. In addition, GraphER is retriever-agnostic and introduces negligible latency overhead. Experiments on multiple retrieval benchmarks demonstrate the effectiveness of the proposed approach. |
| title | GraphER: An Efficient Graph-Based Enrichment and Reranking Method for Retrieval-Augmented Generation |
| topic | Machine Learning Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2603.24925 |