StructGPT: A General Framework for Large Language Model to Reason over Structured Data
Beijing Institute of Big Data Research · Renmin University of China · +1 more institution
Abstract
In this paper, we aim to improve the reasoning ability of large language models (LLMs) over structured data in a unified way. Inspired by the studies on tool augmentation for LLMs, we develop an Iterative Reading-then-Reasoning (IRR) framework to solve question answering tasks based on structured data, called StructGPT. In this framework, we construct the specialized interfaces to collect relevant evidence from structured data (i.e., reading), and let LLMs concentrate on the reasoning task based on the collected information (i.e., reasoning). Specially, we propose an invoking-linearization-generation procedure to support LLMs in reasoning on the structured data with the help of the interfaces. By iterating…
Citation impact
- FWCI
- 28.89
- Percentile
- 100%
- References
- 47
Authors
6- JJJinhao JiangCorresponding
Beijing Institute of Big Data Research, Renmin University of China
- KZKun Zhou
Beijing Institute of Big Data Research, Renmin University of China
- ZDZican Dong
Renmin University of China
- KYKeming Ye
University of Electronic Science and Technology of China
- XZXin Zhao
Beijing Institute of Big Data Research, Renmin University of China
Topics & keywords
- Construct (python library)
- Computer science
- Task (project management)
- Case-based reasoning
- Reading (process)
- Deductive reasoning
- Natural language processing
- Artificial intelligence
- Quality Education