Causal Inference in Large Language Model: A Survey
Abstract: Causal inference has been a pivotal challenge across diverse domains such as medicine and economics, demanding a complicated integration of human knowledge, numerical reasoning, and data processing capabilities. Recent advancements in natural language processing (NLP), particularly with the advent of large language models (LLMs), have introduced transformative 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 their causal problems, methodologies, and present comparison of their evaluation results in different scenarios. Furthermore, we discuss key findings, emerging trends, and outline directions for future research, underscoring the potential implications of integrating LLMs in advancing causal inference methodologies.
Paper Type: Long
Research Area: Language Modeling
Research Area Keywords: causal inference, large language model, causal effect
Contribution Types: Surveys
Languages Studied: English
Submission Number: 5893
Loading