Causal structure learning method and system based on large language model guidance
By acquiring prior constraint information through large-scale language models, the causal structure learning process is simplified, solving the problems of data scarcity and reliance on expert resources in causal relationship discovery, and achieving more accurate and efficient causal relationship discovery.
CN117474087BActive Publication Date: 2026-07-03UNIV OF SCI & TECH OF CHINA
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- UNIV OF SCI & TECH OF CHINA
- Filing Date
- 2023-10-30
- Publication Date
- 2026-07-03
Smart Images
Figure CN117474087B_ABST
Abstract
The application discloses a large language model guidance-based causal structure learning method and system, related schemes can make full use of high-quality and easily accessible prior knowledge provided by a large language model across multiple fields, thereby improving the practicality of causal relationship discovery in actual scenarios, introducing prior knowledge provided by the large language model in causal structure learning, simplifying the search process, and more accurately discovering unknown causal relationships under limited data conditions, thereby providing more accurate and efficient support for data-driven decision-making and prediction; and since the large language model can provide causal prior knowledge across fields, the application has wide application prospects and can realize reliable causal relationship discovery in different fields.
Need to check novelty before this filing date? Find Prior Art