Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.27164 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917536579190784 |
|---|---|
| author | Czyżnikiewicz, Mateusz Tuora, Ryszard Kozakiewicz, Adam Ziętkiewicz, Tomasz Galiński, Mateusz Godziszewski, Michał Karpowicz, Michał Hospedales, Timothy Cornelio, Cristina |
| author_facet | Czyżnikiewicz, Mateusz Tuora, Ryszard Kozakiewicz, Adam Ziętkiewicz, Tomasz Galiński, Mateusz Godziszewski, Michał Karpowicz, Michał Hospedales, Timothy Cornelio, Cristina |
| contents | Retrieval-Augmented Generation (RAG) systems for question answering typically retrieve evidence by semantic similarity between the query and document chunks. While effective for unstructured text, this approach is less reliable on semi-structured corpora where answering may require exact filtering, aggregation, or exhaustive retrieval over structured attributes across multiple documents. Symbolic approaches support such operations, but they are often brittle on noisy natural-language corpora. We address this gap with DualGraph, a RAG framework that represents documents through two complementary views: a Textual Knowledge Graph for semantic retrieval and a Symbolic Knowledge Graph for symbolic querying over typed subject--predicate--object triples. Building on these two components, we provide multiple strategies for selecting or combining semantic and symbolic evidence.We also introduce SpecsQA, a benchmark from a commercial shopping website with semi-structured product documents and manually curated questions spanning open-ended and specification-oriented retrieval. Experiments show that DualGraph consistently outperforms state-of-the-art dense-retrieval, GraphRAG, symbolic, and table-oriented baselines across question types.Code and data are available at https://github.com/corneliocristina/DualGraphRAG. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_27164 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Query Symbolically or Retrieve Semantically? A Dataset and Method for Semi-Structured Question Answering Czyżnikiewicz, Mateusz Tuora, Ryszard Kozakiewicz, Adam Ziętkiewicz, Tomasz Galiński, Mateusz Godziszewski, Michał Karpowicz, Michał Hospedales, Timothy Cornelio, Cristina Artificial Intelligence Retrieval-Augmented Generation (RAG) systems for question answering typically retrieve evidence by semantic similarity between the query and document chunks. While effective for unstructured text, this approach is less reliable on semi-structured corpora where answering may require exact filtering, aggregation, or exhaustive retrieval over structured attributes across multiple documents. Symbolic approaches support such operations, but they are often brittle on noisy natural-language corpora. We address this gap with DualGraph, a RAG framework that represents documents through two complementary views: a Textual Knowledge Graph for semantic retrieval and a Symbolic Knowledge Graph for symbolic querying over typed subject--predicate--object triples. Building on these two components, we provide multiple strategies for selecting or combining semantic and symbolic evidence.We also introduce SpecsQA, a benchmark from a commercial shopping website with semi-structured product documents and manually curated questions spanning open-ended and specification-oriented retrieval. Experiments show that DualGraph consistently outperforms state-of-the-art dense-retrieval, GraphRAG, symbolic, and table-oriented baselines across question types.Code and data are available at https://github.com/corneliocristina/DualGraphRAG. |
| title | Query Symbolically or Retrieve Semantically? A Dataset and Method for Semi-Structured Question Answering |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2605.27164 |