Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.12734 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909801058926592 |
|---|---|
| author | Chen, Yongrui He, Junhao Fu, Linbo Zhang, Shenyu Jin, Rihui Dai, Xinbang Li, Jiaqi Min, Dehai Hu, Nan Zhang, Yuxin Qi, Guilin Huang, Yi Wu, Tongtong |
| author_facet | Chen, Yongrui He, Junhao Fu, Linbo Zhang, Shenyu Jin, Rihui Dai, Xinbang Li, Jiaqi Min, Dehai Hu, Nan Zhang, Yuxin Qi, Guilin Huang, Yi Wu, Tongtong |
| contents | Unified Structured Knowledge Reasoning (USKR) aims to answer natural language questions (NLQs) by using structured sources such as tables, databases, and knowledge graphs in a unified way. Existing USKR methods either rely on employing task-specific strategies or custom-defined representations, which struggle to leverage the knowledge transfer between different SKR tasks or align with the prior of LLMs, thereby limiting their performance. This paper proposes a novel USKR framework named \textsc{Pandora}, which takes advantage of \textsc{Python}'s \textsc{Pandas} API to construct a unified knowledge representation for alignment with LLM pre-training. It employs an LLM to generate textual reasoning steps and executable Python code for each question. Demonstrations are drawn from a memory of training examples that cover various SKR tasks, facilitating knowledge transfer. Extensive experiments on four benchmarks involving three SKR tasks demonstrate that \textsc{Pandora} outperforms existing unified frameworks and competes effectively with task-specific methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_12734 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Pandora: A Code-Driven Large Language Model Agent for Unified Reasoning Across Diverse Structured Knowledge Chen, Yongrui He, Junhao Fu, Linbo Zhang, Shenyu Jin, Rihui Dai, Xinbang Li, Jiaqi Min, Dehai Hu, Nan Zhang, Yuxin Qi, Guilin Huang, Yi Wu, Tongtong Computation and Language Artificial Intelligence Unified Structured Knowledge Reasoning (USKR) aims to answer natural language questions (NLQs) by using structured sources such as tables, databases, and knowledge graphs in a unified way. Existing USKR methods either rely on employing task-specific strategies or custom-defined representations, which struggle to leverage the knowledge transfer between different SKR tasks or align with the prior of LLMs, thereby limiting their performance. This paper proposes a novel USKR framework named \textsc{Pandora}, which takes advantage of \textsc{Python}'s \textsc{Pandas} API to construct a unified knowledge representation for alignment with LLM pre-training. It employs an LLM to generate textual reasoning steps and executable Python code for each question. Demonstrations are drawn from a memory of training examples that cover various SKR tasks, facilitating knowledge transfer. Extensive experiments on four benchmarks involving three SKR tasks demonstrate that \textsc{Pandora} outperforms existing unified frameworks and competes effectively with task-specific methods. |
| title | Pandora: A Code-Driven Large Language Model Agent for Unified Reasoning Across Diverse Structured Knowledge |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2504.12734 |