Large language models and causal inference in collaboration: A comprehensive survey
Xiaoyu Liu, Paiheng Xu, Junda Wu, Jiaxin Yuan, Yifan Yang, Yuhang Zhou, Fuxiao Liu, Tianrui Guan, Haoliang Wang, Tong Yu, Julian McAuley, Wei Ai, Furong Huang
Published in Arxiv, 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.
The paper is available here. Please cite our work if you found it useful,
@misc{liu2024llmcausal,
title={Large Language Models and Causal Inference in Collaboration: A Comprehensive Survey},
author={Xiaoyu Liu and Paiheng Xu and Junda Wu and Jiaxin Yuan and Yifan Yang and Yuhang Zhou and Fuxiao Liu and Tianrui Guan and Haoliang Wang and Tong Yu and Julian McAuley and Wei Ai and Furong Huang},
year={2024},
eprint={2403.09606},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2403.09606},
}