SAGE: Structure Aware Graph Expansion for Retrieval of Heterogeneous Data
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_ | 1866918344793260032 |
|---|---|
| author | Titiya, Prasham Khoja, Rohit Wolfson, Tomer Gupta, Vivek Roth, Dan |
| author_facet | Titiya, Prasham Khoja, Rohit Wolfson, Tomer Gupta, Vivek Roth, Dan |
| contents | Retrieval-augmented question answering over heterogeneous corpora requires connected evidence across text, tables, and graph nodes. While entity-level knowledge graphs support structured access, they are costly to construct and maintain, and inefficient to traverse at query time. In contrast, standard retriever-reader pipelines use flat similarity search over independently chunked text, missing multi-hop evidence chains across modalities. We propose SAGE (Structure Aware Graph Expansion) framework that (i) constructs a chunk-level graph offline using metadata-driven similarities with percentile-based pruning, and (ii) performs online retrieval by running an initial baseline retriever to obtain k seed chunks, expanding first-hop neighbors, and then filtering the neighbors using dense+sparse retrieval, selecting k' additional chunks. We instantiate the initial retriever using hybrid dense+sparse retrieval for implicit cross-modal corpora and SPARK (Structure Aware Planning Agent for Retrieval over Knowledge Graphs) an agentic retriever for explicit schema graphs. On OTT-QA and STaRK, SAGE improves retrieval recall by 5.7 and 8.5 points over baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_16964 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SAGE: Structure Aware Graph Expansion for Retrieval of Heterogeneous Data Titiya, Prasham Khoja, Rohit Wolfson, Tomer Gupta, Vivek Roth, Dan Information Retrieval Retrieval-augmented question answering over heterogeneous corpora requires connected evidence across text, tables, and graph nodes. While entity-level knowledge graphs support structured access, they are costly to construct and maintain, and inefficient to traverse at query time. In contrast, standard retriever-reader pipelines use flat similarity search over independently chunked text, missing multi-hop evidence chains across modalities. We propose SAGE (Structure Aware Graph Expansion) framework that (i) constructs a chunk-level graph offline using metadata-driven similarities with percentile-based pruning, and (ii) performs online retrieval by running an initial baseline retriever to obtain k seed chunks, expanding first-hop neighbors, and then filtering the neighbors using dense+sparse retrieval, selecting k' additional chunks. We instantiate the initial retriever using hybrid dense+sparse retrieval for implicit cross-modal corpora and SPARK (Structure Aware Planning Agent for Retrieval over Knowledge Graphs) an agentic retriever for explicit schema graphs. On OTT-QA and STaRK, SAGE improves retrieval recall by 5.7 and 8.5 points over baselines. |
| title | SAGE: Structure Aware Graph Expansion for Retrieval of Heterogeneous Data |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2602.16964 |