Large Language Models and Causal Inference in Collaboration: A Survey
This is an incremental survey that synthesizes existing research on integrating causal inference with LLMs to address challenges in NLP and AI development.
This survey explores how causal inference can enhance large language models (LLMs) by improving reasoning, fairness, safety, and explainability, while LLMs can aid causal inference through relationship discovery and effect estimation, highlighting their collaborative potential for advancing equitable AI systems.
Causal inference has shown potential in enhancing the predictive accuracy, fairness, robustness, and explainability of Natural Language Processing (NLP) models by capturing causal relationships among variables. The emergence of generative Large Language Models (LLMs) has significantly impacted various NLP domains, particularly through their advanced reasoning capabilities. This survey focuses on evaluating and improving LLMs from a causal view in the following areas: understanding and improving the LLMs' reasoning capacity, addressing fairness and safety issues in LLMs, complementing LLMs with explanations, and handling multimodality. Meanwhile, LLMs' strong reasoning capacities can in turn contribute to the field of causal inference by aiding causal relationship discovery and causal effect estimations. This review explores the interplay between causal inference frameworks and LLMs from both perspectives, emphasizing their collective potential to further the development of more advanced and equitable artificial intelligence systems.