On the Reliability of Large Language Models for Causal Discovery

• URL: http://arxiv.org/abs/2407.19638v2
• Date: Fri, 10 Oct 2025 10:06:02 GMT
• Title: On the Reliability of Large Language Models for Causal Discovery
• Authors: Tao Feng, Lizhen Qu, Niket Tandon, Zhuang Li, Xiaoxi Kang, Gholamreza Haffari,
• Abstract summary: This study investigates the efficacy of Large Language Models (LLMs) in causal discovery.<n>We use newly available open-source LLMs, OLMo and BLOOM, which provide access to their pre-training corpora.<n>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.
• Score: 55.94868919310357
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• CausalFlip: A Benchmark for LLM Causal Judgment Beyond Semantic Matching [50.65932158912512]
  We propose a new causal reasoning benchmark, CausalFlip, to encourage the development of new large language models.<n>CaulFlip consists of causal judgment questions built over event triples that could form different confounder, chain, and collider relations.<n>We evaluate LLMs under multiple training paradigms, including answer-only training, explicit Chain-of-Thought supervision, and a proposed internalized causal reasoning approach.
  arXiv  Detail & Related papers  (2026-02-23T18:06:15Z)
• ExpliCa: Evaluating Explicit Causal Reasoning in Large Language Models [75.05436691700572]
  We introduce ExpliCa, a new dataset for evaluating Large Language Models (LLMs) in explicit causal reasoning. We tested seven commercial and open-source LLMs on ExpliCa through prompting and perplexity-based metrics. Surprisingly, models tend to confound temporal relations with causal ones, and their performance is also strongly influenced by the linguistic order of the events.
  arXiv  Detail & Related papers  (2025-02-21T14:23:14Z)
• Fostering Appropriate Reliance on Large Language Models: The Role of Explanations, Sources, and Inconsistencies [66.30619782227173]
  Large language models (LLMs) can produce erroneous responses that sound fluent and convincing.<n>We identify several features of LLM responses that shape users' reliance.<n>We find that explanations increase reliance on both correct and incorrect responses.<n>We observe less reliance on incorrect responses when sources are provided or when explanations exhibit inconsistencies.
  arXiv  Detail & Related papers  (2025-02-12T16:35:41Z)
• The LLM Effect: Are Humans Truly Using LLMs, or Are They Being Influenced By Them Instead? [60.01746782465275]
  Large Language Models (LLMs) have shown capabilities close to human performance in various analytical tasks. This paper investigates the efficiency and accuracy of LLMs in specialized tasks through a structured user study focusing on Human-LLM partnership.
  arXiv  Detail & Related papers  (2024-10-07T02:30:18Z)
• LLMs Are Prone to Fallacies in Causal Inference [33.9881589703843]
  Recent work shows that causal facts can be effectively extracted from LLMs through prompting. This work investigates if this success is limited to explicitly-mentioned causal facts in the pretraining data which the model can memorize.
  arXiv  Detail & Related papers  (2024-06-18T00:14:07Z)
• ALCM: Autonomous LLM-Augmented Causal Discovery Framework [2.1470800327528843]
  We introduce a new framework, named Autonomous LLM-Augmented Causal Discovery Framework (ALCM), to synergize data-driven causal discovery algorithms and Large Language Models. The ALCM consists of three integral components: causal structure learning, causal wrapper, and LLM-driven causal refiner. We evaluate the ALCM framework by implementing two demonstrations on seven well-known datasets.
  arXiv  Detail & Related papers  (2024-05-02T21:27:45Z)
• CausalBench: A Comprehensive Benchmark for Causal Learning Capability of LLMs [27.362012903540492]
  The ability to understand causality significantly impacts the competence of large language models (LLMs) in output explanation and counterfactual reasoning. The ability to understand causality significantly impacts the competence of large language models (LLMs) in output explanation and counterfactual reasoning.
  arXiv  Detail & Related papers  (2024-04-09T14:40:08Z)
• Evaluating Interventional Reasoning Capabilities of Large Language Models [58.52919374786108]
  Large language models (LLMs) can estimate causal effects under interventions on different parts of a system. We conduct empirical analyses to evaluate whether LLMs can accurately update their knowledge of a data-generating process in response to an intervention. We create benchmarks that span diverse causal graphs (e.g., confounding, mediation) and variable types, and enable a study of intervention-based reasoning.
  arXiv  Detail & Related papers  (2024-04-08T14:15:56Z)
• Large Language Models and Causal Inference in Collaboration: A Comprehensive Survey [46.4375135354838]
  Causal inference has shown potential in enhancing the predictive accuracy, fairness, robustness, and explainability of Natural Language Processing (NLP) models. The emergence of generative Large Language Models (LLMs) has significantly impacted various NLP domains.
  arXiv  Detail & Related papers  (2024-03-14T17:47:20Z)
• Discovery of the Hidden World with Large Language Models [95.58823685009727]
  This paper presents Causal representatiOn AssistanT (COAT) that introduces large language models (LLMs) to bridge the gap. LLMs are trained on massive observations of the world and have demonstrated great capability in extracting key information from unstructured data. COAT also adopts CDs to find causal relations among the identified variables as well as to provide feedback to LLMs to iteratively refine the proposed factors.
  arXiv  Detail & Related papers  (2024-02-06T12:18:54Z)
• Is Knowledge All Large Language Models Needed for Causal Reasoning? [11.476877330365664]
  This paper explores the causal reasoning of large language models (LLMs) to enhance their interpretability and reliability in advancing artificial intelligence. We propose a novel causal attribution model that utilizes do-operators" for constructing counterfactual scenarios.
  arXiv  Detail & Related papers  (2023-12-30T04:51:46Z)
• Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation [109.8527403904657]
  We show that large language models (LLMs) possess unwavering confidence in their knowledge and cannot handle the conflict between internal and external knowledge well. Retrieval augmentation proves to be an effective approach in enhancing LLMs' awareness of knowledge boundaries. We propose a simple method to dynamically utilize supporting documents with our judgement strategy.
  arXiv  Detail & Related papers  (2023-07-20T16:46:10Z)
• From Query Tools to Causal Architects: Harnessing Large Language Models for Advanced Causal Discovery from Data [19.264745484010106]
  Large Language Models (LLMs) exhibit exceptional abilities for causal analysis between concepts in numerous societally impactful domains. Recent research on LLM performance in various causal discovery and inference tasks has given rise to a new ladder in the classical three-stage framework of causality. We propose a novel framework that combines knowledge-based LLM causal analysis with data-driven causal structure learning.
  arXiv  Detail & Related papers  (2023-06-29T12:48:00Z)
• Can Large Language Models Infer Causation from Correlation? [104.96351414570239]
  We test the pure causal inference skills of large language models (LLMs) We formulate a novel task Corr2Cause, which takes a set of correlational statements and determines the causal relationship between the variables. We show that these models achieve almost close to random performance on the task.
  arXiv  Detail & Related papers  (2023-06-09T12:09:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.