Prompt-based vs. Fine-tuned LLMs Toward Causal Graph Verification

This work aims toward an application of NLP technology for automatic verification of causal graphs using text sources. A causal graph is often derived from unsupervised causal discovery methods and requires manual evaluation from human experts. NLP technologies, i.e., LLMs such as BERT and ChatGPT, can potentially be used to verify the resulted causal graph by predicting if causal relation can be observed between node pairs based on the textual context. In this work, we compare the performance of two types of NLP models: (1) Pre-trained language models fine-tuned for causal relation classification task and, (2) prompt-based LLMs. Contrasted to previous studies where prompt-based LLMs work relatively well over a set of diverse tasks, preliminary experiments on biomedical and open-domain datasets suggest that the fine-tuned models far outperform the prompt-based LLMs, up to 20.5 points improvement of F1 score. We shared the code and the pre-processed datasets in our repository.