Causal Inference with Large Language Model: A Survey

TL;DR

This survey reviews how large language models are being applied to causal inference, highlighting recent progress, comparing evaluation results, and discussing future research directions in this emerging intersection.

Contribution

It provides a comprehensive overview of the integration of LLMs into causal inference, summarizing methods, results, and future research opportunities.

Findings

LLMs show promising potential in causal inference tasks

Evaluation results vary across different causal scenarios

Future research should focus on improving LLMs' causal reasoning capabilities

Abstract

Causal inference has been a pivotal challenge across diverse domains such as medicine and economics, demanding a complicated integration of human knowledge, mathematical reasoning, and data mining capabilities. Recent advancements in natural language processing (NLP), particularly with the advent of large language models (LLMs), have introduced promising opportunities for traditional causal inference tasks. This paper reviews recent progress in applying LLMs to causal inference, encompassing various tasks spanning different levels of causation. We summarize the main causal problems and approaches, and present a comparison of their evaluation results in different causal scenarios. Furthermore, we discuss key findings and outline directions for future research, underscoring the potential implications of integrating LLMs in advancing causal inference methodologies.