CARE: Turning LLMs Into Causal Reasoning Expert
Preprint
Abstract
Large language models (LLMs) have recently demonstrated impressive capabilities across a range of reasoning and generation tasks. However, research studies have shown that LLMs lack the ability to identify causal relationships, a fundamental cornerstone of human intelligence. We first conduct an exploratory investigation of LLMs' behavior when asked to perform a causal-discovery task and find that they mostly rely on the semantic meaning of variable names, ignoring the observation data. This is unsurprising, given that LLMs were never trained to process structural datasets. To first tackle this challenge, we prompt the LLMs with the outputs of established causal discovery algorithms designed for observational datasets. These algorithm outputs effectively serve as the sufficient statistics of the observation data. However, quite surprisingly, we find that prompting the LLMs with these sufficient statistics decreases the LLMs' performance in causal discovery. To address this current limitation, we propose CARE, a framework that enhances LLMs' causal-reasoning ability by teaching them to effectively utilize the outputs of established causal-discovery algorithms through supervised fine-tuning. Experimental results show that a finetuned Qwen2.5-1.5B model produced by CARE significantly outperforms both traditional causal-discovery algorithms and state-of-the-art LLMs with over a thousand times more parameters, demonstrating effective utilization of its own knowledge and the external algorithmic clues.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?2024
- A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery2024
- CLadder: Assessing Causal Reasoning in Language Models2023
- Fast Scalable and Accurate Discovery of DAGs Using the Best Order Score Search and Grow Shrink Trees2023
- Chain-Of-Thought Prompting Elicits Reasoning in Large Language Models2022
- Local Computations with Probabilities on Graphical Structures and Their Application to Expert SystemsJournal of the Royal Statistical Society Series B: Statistical Methodology, 1988
- A new look at the statistical model identificationIEEE Transactions on Automatic Control, 1974