NeuSym-RAG: Hybrid Neural Symbolic Retrieval with Multiview Structuring for PDF Question Answering
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916770234761216 |
|---|---|
| author | Cao, Ruisheng Zhang, Hanchong Huang, Tiancheng Kang, Zhangyi Zhang, Yuxin Sun, Liangtai Li, Hanqi Miao, Yuxun Fan, Shuai Chen, Lu Yu, Kai |
| author_facet | Cao, Ruisheng Zhang, Hanchong Huang, Tiancheng Kang, Zhangyi Zhang, Yuxin Sun, Liangtai Li, Hanqi Miao, Yuxun Fan, Shuai Chen, Lu Yu, Kai |
| contents | The increasing number of academic papers poses significant challenges for researchers to efficiently acquire key details. While retrieval augmented generation (RAG) shows great promise in large language model (LLM) based automated question answering, previous works often isolate neural and symbolic retrieval despite their complementary strengths. Moreover, conventional single-view chunking neglects the rich structure and layout of PDFs, e.g., sections and tables. In this work, we propose NeuSym-RAG, a hybrid neural symbolic retrieval framework which combines both paradigms in an interactive process. By leveraging multi-view chunking and schema-based parsing, NeuSym-RAG organizes semi-structured PDF content into both the relational database and vectorstore, enabling LLM agents to iteratively gather context until sufficient to generate answers. Experiments on three full PDF-based QA datasets, including a self-annotated one AIRQA-REAL, show that NeuSym-RAG stably defeats both the vector-based RAG and various structured baselines, highlighting its capacity to unify both retrieval schemes and utilize multiple views. Code and data are publicly available at https://github.com/X-LANCE/NeuSym-RAG. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_19754 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | NeuSym-RAG: Hybrid Neural Symbolic Retrieval with Multiview Structuring for PDF Question Answering Cao, Ruisheng Zhang, Hanchong Huang, Tiancheng Kang, Zhangyi Zhang, Yuxin Sun, Liangtai Li, Hanqi Miao, Yuxun Fan, Shuai Chen, Lu Yu, Kai Computation and Language Artificial Intelligence The increasing number of academic papers poses significant challenges for researchers to efficiently acquire key details. While retrieval augmented generation (RAG) shows great promise in large language model (LLM) based automated question answering, previous works often isolate neural and symbolic retrieval despite their complementary strengths. Moreover, conventional single-view chunking neglects the rich structure and layout of PDFs, e.g., sections and tables. In this work, we propose NeuSym-RAG, a hybrid neural symbolic retrieval framework which combines both paradigms in an interactive process. By leveraging multi-view chunking and schema-based parsing, NeuSym-RAG organizes semi-structured PDF content into both the relational database and vectorstore, enabling LLM agents to iteratively gather context until sufficient to generate answers. Experiments on three full PDF-based QA datasets, including a self-annotated one AIRQA-REAL, show that NeuSym-RAG stably defeats both the vector-based RAG and various structured baselines, highlighting its capacity to unify both retrieval schemes and utilize multiple views. Code and data are publicly available at https://github.com/X-LANCE/NeuSym-RAG. |
| title | NeuSym-RAG: Hybrid Neural Symbolic Retrieval with Multiview Structuring for PDF Question Answering |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2505.19754 |