LLM4Causal: Democratized Causal Tools for Everyone via Large Language Model

TL;DR

This paper introduces LLM4Causal, an open-source fine-tuned large language model designed to perform causal inference tasks, interpret results, and provide accessible causal reasoning tools for users, enhancing LLM capabilities in structured causal reasoning.

Contribution

The work presents a novel fine-tuning approach with new datasets enabling LLMs to identify causal tasks, execute causal functions, and interpret results, making causal reasoning more accessible.

Findings

LLM4Causal outperforms baselines in causal problem solving

It provides clear, interpretable causal explanations

End-to-end causal inference is effectively achieved

Abstract

Large Language Models (LLMs) have shown their success in language understanding and reasoning on general topics. However, their capability to perform inference based on user-specified structured data and knowledge in corpus-rare concepts, such as causal decision-making is still limited. In this work, we explore the possibility of fine-tuning an open-sourced LLM into LLM4Causal, which can identify the causal task, execute a corresponding function, and interpret its numerical results based on users' queries and the provided dataset. Meanwhile, we propose a data generation process for more controllable GPT prompting and present two instruction-tuning datasets: (1) Causal-Retrieval-Bench for causal problem identification and input parameter extraction for causal function calling and (2) Causal-Interpret-Bench for in-context causal interpretation. By conducting end-to-end evaluations and two ablation studies, we showed that LLM4Causal can deliver end-to-end solutions for causal problems and provide easy-to-understand answers, which significantly outperforms the baselines.