Zero-shot Causal Graph Extrapolation from Text via LLMs (2312.14670v1)
Abstract: We evaluate the ability of LLMs to infer causal relations from natural language. Compared to traditional natural language processing and deep learning techniques, LLMs show competitive performance in a benchmark of pairwise relations without needing (explicit) training samples. This motivates us to extend our approach to extrapolating causal graphs through iterated pairwise queries. We perform a preliminary analysis on a benchmark of biomedical abstracts with ground-truth causal graphs validated by experts. The results are promising and support the adoption of LLMs for such a crucial step in causal inference, especially in medical domains, where the amount of scientific text to analyse might be huge, and the causal statements are often implicit.
- Large Language Models for Biomedical Causal Graph Construction. arXiv preprint arXiv:2301.12473.
- On Pearl’s hierarchy and the foundations of causal inference. In Probabilistic and causal inference: the works of judea pearl, 507–556. Association for Computing Machinery.
- Chickering, D. M. 2002. Optimal structure identification with greedy search. Journal of machine learning research, 3(Nov): 507–554.
- Semeval-2010 task 8: Multi-way classification of semantic relations between pairs of nominals. arXiv preprint arXiv:1911.10422.
- A survey on knowledge graphs: Representation, acquisition, and applications. IEEE transactions on neural networks and learning systems, 33(2): 494–514.
- Can Large Language Models Infer Causation from Correlation? arXiv preprint arXiv:2306.05836.
- A survey on text classification: From traditional to deep learning. ACM Transactions on Intelligent Systems and Technology (TIST), 13(2): 1–41.
- Fulminant type 1 diabetes: a comprehensive review of an autoimmune condition. Diabetes/Metabolism Research and Reviews, 36(6): e3317.
- Large language models and knowledge graphs: Opportunities and challenges. arXiv preprint arXiv:2308.06374.
- Pearl, J. 2009. Causality. Cambridge university press.
- Rehder, B. 2017. Reasoning with causal cycles. Cognitive science, 41: 944–1002.
- Prompt programming for large language models: Beyond the few-shot paradigm. In Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems, 1–7.
- Deep learning in medical image analysis. Annual review of biomedical engineering, 19: 221–248.
- Towards expert-level medical question answering with large language models. arXiv preprint arXiv:2305.09617.
- Causation, prediction, and search. MIT press.
- Comparative study of CNN and RNN for natural language processing. arXiv preprint arXiv:1702.01923.
- Approximating counterfactual bounds while fusing observational, biased and randomised data sources. International Journal of Approximate Reasoning, 162: 109023.
- Understanding causality with large language models: Feasibility and opportunities. arXiv preprint arXiv:2304.05524.