Integrating Large Language Model for Improved Causal Discovery

2023/06/29 by Taiyu Ban, Ban, Taiyu, L L Chen +8 · 12 citations
Computer Science · Social Sciences · #Artificial Intelligence (cs.AI) #Computational and Text Analysis Methods #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2306.16902

openalex publication_date 2023/06/29 · openalex created_date 2023/07/01 · openalex updated_date 2026/07/28

Abstract

Recovering the structure of causal graphical models from observational data is an essential yet challenging task for causal discovery in scientific scenarios. Domain-specific causal discovery usually relies on expert validation or prior analysis to improve the reliability of recovered causality, which is yet limited by the scarcity of expert resources. Recently, Large Language Models (LLM) have been used for causal analysis across various domain-specific scenarios, suggesting its potential as autonomous expert roles in guiding data-based structure learning. However, integrating LLMs into causal discovery faces challenges due to inaccuracies in LLM-based reasoning on revealing the actual causal structure. To address this challenge, we propose an error-tolerant LLM-driven causal discovery framework. The error-tolerant mechanism is designed three-fold with sufficient consideration on potential inaccuracies. In the LLM-based reasoning process, an accuracy-oriented prompting strategy restricts causal analysis to a reliable range. Next, a knowledge-to-structure transition aligns LLM-derived causal statements with structural causal interactions. In the structure learning process, the goodness-of-fit to data and adherence to LLM-derived priors are balanced to further address prior inaccuracies. Evaluation of eight real-world causal structures demonstrates the efficacy of our LLM-driven approach in improving data-based causal discovery, along with its robustness to inaccurate LLM-derived priors. Codes are available at https://github.com/tyMadara/LLM-CD.

Cited by

• CARE: Turning LLMs Into Causal Reasoning Expert
• Robust Causal Discovery under Imperfect Structural Constraints
• Bayesian Network Structure Discovery Using Large Language Models
• Linear Causal Discovery with Interventional Constraints
• Realizing LLMs' Causal Potential Requires Science-Grounded, Novel Benchmarks
• On the Problem of Consistent Anomalies in Zero-Shot Industrial Anomaly Detection
• Executable Counterfactuals: Improving LLMs' Causal Reasoning Through Code
• KEO: Knowledge Extraction on OMIn via Knowledge Graphs and RAG for Safety-Critical Aviation Maintenance
• Revealing Multimodal Causality with Large Language Models
• Causal Reasoning Elicits Controllable 3D Scene Generation
• Score-informed Neural Operator for Enhancing Ordering-based Causal Discovery
• Expert-aided causal discovery of ancestral graphs

Related

• ALCM: Autonomous LLM-Augmented Causal Discovery Framework
• Causal Structure Learning Supervised by Large Language Model
• Large Language Models for Causal Discovery: Current Landscape and Future Directions
• Causal Reasoning and Large Language Models: Opening a New Frontier for Causality
• On the Reliability of Large Language Models for Causal Discovery