On the Reliability of Large Language Models for Causal Discovery

ACL ARR 2024 December Submission2069 Authors

Abstract: This study investigates the efficacy of Large Language Models (LLMs) in causal discovery. Using newly available open-source LLMs, OLMo and BLOOM, which provide access to their pre-training corpora, we investigate how LLMs address causal discovery through three research questions. We examine: (i) the impact of memorization for accurate causal relation prediction, (ii) the influence of incorrect causal relations in pre-training data, and (iii) the contextual nuances that influence LLMs' understanding of causal relations. Our findings indicate that while LLMs are effective in recognizing causal relations that occur frequently in pre-training data, their ability to generalize to new or rare causal relations is limited. Moreover, the presence of incorrect causal relations significantly undermines the confidence of LLMs in corresponding correct causal relations, and the contextual information critically affects the outcomes of LLMs to discern causal connections between random variables.

Paper Type: Long

Research Area: Special Theme (conference specific)

Research Area Keywords: Generalization of LLM-based Causal Discovery Methods, Causal Discovery, Large Language Model

Contribution Types: Model analysis & interpretability, Data analysis

Languages Studied: English

Submission Number: 2069