Back to Search Start Over

Large Language Models and Causal Inference in Collaboration: A Comprehensive Survey

Authors :
Liu, Xiaoyu
Xu, Paiheng
Wu, Junda
Yuan, Jiaxin
Yang, Yifan
Zhou, Yuhang
Liu, Fuxiao
Guan, Tianrui
Wang, Haoliang
Yu, Tong
McAuley, Julian
Ai, Wei
Huang, Furong
Publication Year :
2024

Abstract

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.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2403.09606
Document Type :
Working Paper