mlsanityData to 7 Oct 2026

Causal Discovery with Language Models as Imperfect Experts

arXiv 2307.02390 ↗First posted 5 Jul 2023cs.AI cs.CL cs.LGcited by 62

Not on the map. Why?

Abstract (arXiv)

Understanding the causal relationships that underlie a system is a fundamental prerequisite to accurate decision-making. In this work, we explore how expert knowledge can be used to improve the data-driven identification of causal graphs, beyond Markov equivalence classes. In doing so, we consider a setting where we can query an expert about the orientation of causal relationships between variables, but where the expert may provide erroneous information. We propose strategies for amending such expert knowledge based on consistency properties, e.g., acyclicity and conditional independencies in the equivalence class. We then report a case study, on real data, where a large language model is used as an imperfect expert.

Key facts. Cited by 62 papers in the map (data through 7 Oct 2026). Builds on 15 of its 37 references that are in the map. First posted on arXiv 5 Jul 2023.

Builds on

15 of 37 references.

References · 15

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  4. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  5. 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 745
  6. 2023Causal Reasoning and Large Language Models: Opening a New Frontier for Causalitycited by 348
  7. 2020Differentiable Causal Discovery from Interventional Datacited by 218
  8. 2013Causal Inference and Causal Explanation with Background Knowledgecited by 168
  9. 2013Causal Inference in the Presence of Latent Variables and Selection Biascited by 165
  10. 2023Can large language models build causal graphs?cited by 72
  11. 2022LMPriors: Pre-Trained Language Models as Task-Specific Priorscited by 56
  12. 2023Causal-Discovery Performance of ChatGPT in the context of Neuropathic Pain Diagnosiscited by 36
3 more
  1. 2021The impact of prior knowledge on causal structure learningcited by 35
  2. 2022Can Foundation Models Talk Causality?cited by 30
  3. 2021Typing assumptions improve identification in causal discoverycited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 19; 2025: 17; 2026: 23.

62 papers.

Sort:

By area:

  1. 2024Efficient Causal Graph Discovery Using Large Language Modelscited by 51
  2. 2023Causal Order: The Key to Leveraging Imperfect Experts in Causal Inferencecited by 46
  3. 2025Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?cited by 36
  4. 2024Integrating Large Language Models in Causal Discovery: A Statistical Causal Approachcited by 31
  5. 2024ALCM: Autonomous LLM-Augmented Causal Discovery Frameworkcited by 29
  6. 2024Large Language Models for Causal Discovery: Current Landscape and Future Directionscited by 25
  7. 2024Large Language Models are Effective Priors for Causal Graph Discoverycited by 23
  8. 2025Robust Reward Modeling via Causal Rubricscited by 18
  9. 2024Large Language Models for Constrained-Based Causal Discoverycited by 15
  10. 2024Cloud Atlas: Efficient Fault Localization for Cloud Systems using Language Models and Causal Insightcited by 11
  11. 2024Exploring Multi-Modal Data with Tool-Augmented LLM Agents for Precise Causal Discoverycited by 11
  12. 2024Discovering and Reasoning of Causality in the Hidden World with Large Language Modelscited by 10
38 more
  1. 2025Can Large Language Models Help Experimental Design for Causal Discovery?cited by 10
  2. 2025CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Taskscited by 8
  3. 2024MALLM-GAN: Multi-Agent Large Language Model as Generative Adversarial Network for Synthesizing Tabular Datacited 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. 2024Evaluating Interventional Reasoning Capabilities of Large Language Modelscited by 6
  7. 2024LLM-initialized Differentiable Causal Discoverycited by 6
  8. 2023An Explainable AI Approach to Large Language Model Assisted Causal Model Auditing and Developmentcited by 5
  9. 2024Simulating Policy Impacts: Developing a Generative Scenario Writing Method to Evaluate the Perceived Effects of Regulationcited by 5
  10. 2025Ice Cream Doesn't Cause Drowning: Benchmarking LLMs Against Statistical Pitfalls in Causal Inferencecited by 5
  11. 2025No Black Boxes: Interpretable and Interactable Predictive Healthcare with Knowledge-Enhanced Agentic Causal Discoverycited by 5
  12. 2025Bayesian Network Structure Discovery Using Large Language Modelscited by 5
  13. 2025Realizing LLMs' Causal Potential Requires Science-Grounded, Novel Benchmarkscited by 4
  14. 2023Learned Causal Method Predictioncited by 3
  15. 2024Scalability of Bayesian Network Structure Elicitation with Large Language Models: a Novel Methodology and Comparative Analysiscited by 3
  16. 2024CausalChat: Interactive Causal Model Development and Refinement Using Large Language Modelscited by 3
  17. 2025Revealing Multimodal Causality with Large Language Modelscited by 3
  18. 2026Eroding the Truth-Default: A Causal Analysis of Human Susceptibility to Foundation Model Hallucinations and Disinformation in the Wildcited by 3
  19. 2026CausalEvolve: Towards Open-Ended Discovery with Causal Scratchpadcited by 3
  20. 2025Score-informed Neural Operator for Enhancing Ordering-based Causal Discoverycited by 2
  21. 2026CauScientist: Teaching LLMs to Respect Data for Causal Discoverycited by 2
  22. 2026Causal Ensemble Agent: Hierarchical Causal Discovery with LLM-guided Expert Reweightingcited by 2
  23. 2024Regularized Multi-LLMs Collaboration for Enhanced Score-based Causal Discoverycited by 1
  24. 2025Your Assumed DAG is Wrong and Here's How To Deal With Itcited by 1
  25. 2025Less Greedy Equivalence Searchcited by 1
  26. 2025CARE: Turning LLMs Into Causal Reasoning Expertcited by 1
  27. 2026Linear-LLM-SCM: Benchmarking LLMs for Coefficient Elicitation in Linear-Gaussian Causal Modelscited by 1
  28. 2026CauTion: Knowing When to Trust LLMs for Ensemble Causal Discoverycited by 1
  29. 2024Membership Testing in Markov Equivalence Classes via Independence Query Oraclescited by 0
  30. 2024Retrieving Classes of Causal Orders with Inconsistent Knowledge Basescited by 0
  31. 2025Sequential Causal Discovery with Noisy Language Model Priorscited by 0
  32. 2025GRID: Graph-based Reasoning for Intervention and Discovery in Built Environmentscited by 0
  33. 2025Linear Causal Discovery with Interventional Constraintscited by 0
  34. 2026Step-by-Step Causality: Transparent Causal Discovery with Multi-Agent Tree-Query and Adversarial Confidence Estimationcited by 0
  35. 2026CaST: Causal Discovery via Spatio-Temporal Graphs in Disaster Tweetscited by 0
  36. 2026DMCD: Semantic-Statistical Framework for Causal Discoverycited by 0
  37. 2026Causal Discovery Should Embrace the Wisdom of the Crowdcited by 0
  38. 2026Eliciting associations between clinical variables from LLMs via comparison questions across populationscited by 0

50 most cited of 62 All 62 (JSON)