mlsanityData to 7 Oct 2026

Large Language Models for Constrained-Based Causal Discovery

arXiv 2406.07378 ↗First posted 11 Jun 2024cs.AI cs.CLcited by 15

Not on the map. Why?

Abstract (arXiv)

Causality is essential for understanding complex systems, such as the economy, the brain, and the climate. Constructing causal graphs often relies on either data-driven or expert-driven approaches, both fraught with challenges. The former methods, like the celebrated PC algorithm, face issues with data requirements and assumptions of causal sufficiency, while the latter demand substantial time and domain knowledge. This work explores the capabilities of Large Language Models (LLMs) as an alternative to domain experts for causal graph generation. We frame conditional independence queries as prompts to LLMs and employ the PC algorithm with the answers. The performance of the LLM-based conditional independence oracle on systems with known causal graphs shows a high degree of variability. We improve the performance through a proposed statistical-inspired voting schema that allows some control over false-positive and false-negative rates. Inspecting the chain-of-thought argumentation, we find causal reasoning to justify its answer to a probabilistic query. We show evidence that knowledge-based CIT could eventually become a complementary tool for data-driven causal discovery.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 22 of its 63 references that are in the map. First posted on arXiv 11 Jun 2024.

Builds on

22 of 63 references.

References · 22

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2023Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedbackcited by 788
  5. 2023Large Language Modelscited by 774
  6. 2023Causal Reasoning and Large Language Models: Opening a New Frontier for Causalitycited by 348
  7. 2013Causal Inference and Causal Explanation with Background Knowledgecited by 168
  8. 2023Causal Parrots: Large Language Models May Talk Causality But Are Not Causalcited by 146
  9. 2023Black-Box Prompt Optimization: Aligning Large Language Models without Model Trainingcited by 122
  10. 2020High-recall causal discovery for autocorrelated time series with latent confounderscited by 82
  11. 2013Learning Equivalence Classes of Bayesian Networks Structurescited by 75
  12. 2023Can large language models build causal graphs?cited by 72
10 more
  1. 2023Causal Discovery with Language Models as Imperfect Expertscited by 62
  2. 2023Integrating Large Language Model for Improved Causal Discoverycited by 54
  3. 2023Causal Order: The Key to Leveraging Imperfect Experts in Causal Inferencecited by 46
  4. 2023Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactualscited by 44
  5. 2021The impact of prior knowledge on causal structure learningcited by 35
  6. 2023Discovering Causal Relations and Equations from Datacited by 33
  7. 2013Learning Bayesian Networks: A Unification for Discrete and Gaussian Domainscited by 21
  8. 2021Bayesian structure learning and sampling of Bayesian networks with the R package BiDAGcited by 17
  9. 2023Expert-Aided Causal Discovery of Ancestral Graphscited by 8
  10. 2014Scoring and Searching over Bayesian Networks with Causal and Associative Priorscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 7; 2026: 3.

15 papers.

Sort:

By area:

  1. 2024Multi-Agent Causal Discovery Using Large Language Modelscited by 26
  2. 2025CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Taskscited by 8
  3. 2024Mining Causality: AI-Assisted Search for Instrumental Variablescited by 7
  4. 2024Prompting Strategies for Enabling Large Language Models to Infer Causation from Correlationcited by 7
  5. 2025LLM Cannot Discover Causality, and Should Be Restricted to Non-Decisional Support in Causal Discoverycited by 7
  6. 2025Bayesian Network Structure Discovery Using Large Language Modelscited by 5
  7. 2024Causal Inference with Latent Variables: Recent Advances and Future Prospectivescited by 4
  8. 2025Revealing Multimodal Causality with Large Language Modelscited by 3
  9. 2025Learning to Defer for Causal Discovery with Imperfect Expertscited by 2
  10. 2026Leveraging Large Language Models for Causal Discovery: a Constraint-based, Argumentation-driven Approachcited by 1
  11. 2024Retrieving Classes of Causal Orders with Inconsistent Knowledge Basescited by 0
  12. 2025Improving constraint-based discovery with robust propagation and reliable LLM priorscited by 0
3 more
  1. 2025Guide: Generalized-Prior and Data Encoders for DAG Estimationcited by 0
  2. 2026Step-by-Step Causality: Transparent Causal Discovery with Multi-Agent Tree-Query and Adversarial Confidence Estimationcited by 0
  3. 2026EviDAG: Auditable Causal DAG Authoring with Biomedical Literaturecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024CausalGraph2LLM: Evaluating LLMs for Causal Queries
  2. 2024Causal Graph Discovery with Retrieval-Augmented Generation based Large Language Models
  3. 2025HOLOGRAPH: Active Causal Discovery via Sheaf-Theoretic Alignment of Large Language Model Priors
  4. 2025Causal Reasoning in Pieces: Modular In-Context Learning for Causal Discovery
  5. 2024ALCM: Autonomous LLM-Augmented Causal Discovery Framework
  6. 2024LLM-initialized Differentiable Causal Discovery
  7. 2025Causal MAS: A Survey of Large Language Model Architectures for Discovery and Effect Estimation
  8. 2026Why LLMs Fail at Causal Discovery and How Interventional Agents Escape