LLM4Causal: Democratized Causal Tools for Everyone via Large Language Model
This provides democratized causal analysis tools for users needing structured data inference, though it's an incremental application of existing methods to a new domain.
The researchers tackled the problem of limited LLM capabilities for causal inference by fine-tuning an open-sourced LLM into LLM4Causal, which identifies causal tasks, executes functions, and interprets results based on user queries and datasets, showing it significantly outperforms baselines in end-to-end evaluations.
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.