mlsanityData to 7 Oct 2026

Causal Parrots: Large Language Models May Talk Causality But Are Not Causal

arXiv 2308.13067 ↗First posted 24 Aug 2023cs.AI cs.CLcited by 146

Not on the map. Why?

Cited by 51 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Some argue scale is all what is needed to achieve AI, covering even causal models. We make it clear that large language models (LLMs) cannot be causal and give reason onto why sometimes we might feel otherwise. To this end, we define and exemplify a new subgroup of Structural Causal Model (SCM) that we call meta SCM which encode causal facts about other SCM within their variables. We conjecture that in the cases where LLM succeed in doing causal inference, underlying was a respective meta SCM that exposed correlations between causal facts in natural language on whose data the LLM was ultimately trained. If our hypothesis holds true, then this would imply that LLMs are like parrots in that they simply recite the causal knowledge embedded in the data. Our empirical analysis provides favoring evidence that current LLMs are even weak `causal parrots.'

Key facts. Cited by 146 papers in the map (data through 7 Oct 2026). Builds on 29 of its 71 references that are in the map. First posted on arXiv 24 Aug 2023.

Builds on

29 of 71 references.

References · 29

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2023GPT-4 Technical Reportcited by 18,132
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  6. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  7. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  8. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  9. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  10. 2020The Pile: An 800GB Dataset of Diverse Text for Language Modelingcited by 2,346
  11. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
  12. 2023Causal Reasoning and Large Language Models: Opening a New Frontier for Causalitycited by 348
17 more
  1. 2019Causality for Machine Learningcited by 242
  2. 2021Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyondcited by 177
  3. 2023Can Large Language Models Infer Causation from Correlation?cited by 142
  4. 2016Foundations of Structural Causal Models with Cycles and Latent Variablescited by 134
  5. 2022CommonsenseQA 2.0: Exposing the Limits of AI through Gamificationcited by 108
  6. 2020Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Datacited by 99
  7. 2021The Causal-Neural Connection: Expressiveness, Learnability, and Inferencecited by 97
  8. 2022On the Paradox of Learning to Reason from Datacited by 93
  9. 2022CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behaviorcited by 54
  10. 2021CausalCity: Complex Simulations with Agency for Causal Discovery and Reasoningcited by 23
  11. 2020Causal BERT : Language models for causality detection between events expressed in textcited by 22
  12. 2021Interventional Sum-Product Networks: Causal Inference with Tractable Probabilistic Modelscited by 22
  13. 2022WikiWhy: Answering and Explaining Cause-and-Effect Questionscited by 21
  14. 2020Artificial Intelligence is stupid and causal reasoning won't fix itcited by 20
  15. 2018Detecting non-causal artifacts in multivariate linear regression modelscited by 16
  16. 2022Selection Bias Induced Spurious Correlations in Large Language Modelscited by 9
  17. 2018The 30-Year Cycle In The AI Debatecited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 9; 2024: 52; 2025: 48; 2026: 37.

146 papers.

Sort:

By area:

  1. 2025Agentic Large Language Models, a surveycited by 105
  2. 2023CLadder: Assessing Causal Reasoning in Language Modelscited by 102
  3. 2023DyVal: Dynamic Evaluation of Large Language Models for Reasoning Taskscited by 100
  4. 2024Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Surveycited by 82
  5. 2024Robust agents learn causal world modelscited by 81
  6. 2023Visual cognition in multimodal large language modelscited by 38
  7. 2025Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?cited by 36
  8. 2024The broader spectrum of in-context learningcited by 33
  9. 2024The Essential Role of Causality in Foundation World Models for Embodied AIcited by 32
  10. 2024Integrating Large Language Models in Causal Discovery: A Statistical Causal Approachcited by 31
  11. 2024Causal Inference with Large Language Model: A Surveycited by 31
  12. 2024Do Vision-Language Models Really Understand Visual Language?cited by 29
38 more
  1. 2024Large Language Models and Causal Inference in Collaboration: A Surveycited by 26
  2. 2024Multi-Agent Causal Discovery Using Large Language Modelscited by 26
  3. 2024Large Language Models for Causal Discovery: Current Landscape and Future Directionscited by 25
  4. 2025Thinking Machines: A Survey of LLM based Reasoning Strategiescited by 25
  5. 2024Causality for Large Language Modelscited by 24
  6. 2024Cause and Effect: Can Large Language Models Truly Understand Causality?cited by 23
  7. 2024LLMs Are Prone to Fallacies in Causal Inferencecited by 21
  8. 2025The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Directioncited by 21
  9. 2025CounterBench: Evaluating and Improving Counterfactual Reasoning in Large Language Modelscited by 19
  10. 2025Agentic AI Needs a Systems Theorycited by 19
  11. 2024Causal Evaluation of Language Modelscited by 18
  12. 2024End-To-End Causal Effect Estimation from Unstructured Natural Language Datacited by 18
  13. 2024Quantifying Generalization Complexity for Large Language Modelscited by 18
  14. 2025Large language models for artificial general intelligence (AGI): A survey of foundational principles and approachescited by 18
  15. 2023Towards Causal Foundation Model: on Duality between Causal Inference and Attentioncited by 17
  16. 2024Causal Graph Discovery with Retrieval-Augmented Generation based Large Language Modelscited by 16
  17. 2024Large Language Models for Constrained-Based Causal Discoverycited by 15
  18. 2025Abduct, Act, Predict: Scaffolding Causal Inference for Automated Failure Attribution in Multi-Agent Systemscited by 14
  19. 2023Do large language models solve verbal analogies like children do?cited by 13
  20. 2024A Critical Review of Causal Reasoning Benchmarks for Large Language Modelscited by 13
  21. 2024CausalEval: Towards Better Causal Reasoning in Language Modelscited by 13
  22. 2024On the Reliability of Large Language Models for Causal Discoverycited by 12
  23. 2024Failure Modes of LLMs for Causal Reasoning on Narrativescited by 12
  24. 2024Exploring Multi-Modal Data with Tool-Augmented LLM Agents for Precise Causal Discoverycited by 11
  25. 2025Epistemological Fault Lines Between Human and Artificial Intelligencecited by 11
  26. 2024CELLO: Causal Evaluation of Large Vision-Language Modelscited by 10
  27. 2024Causal Agent based on Large Language Modelcited by 10
  28. 2025Can Large Language Models Help Experimental Design for Causal Discovery?cited by 10
  29. 2024C2P: Featuring Large Language Models with Causal Reasoningcited by 8
  30. 2024Language Agents Meet Causality -- Bridging LLMs and Causal World Modelscited by 8
  31. 2025CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Taskscited by 8
  32. 2024Counterfactual Causal Inference in Natural Language with Large Language Modelscited by 7
  33. 2024Prompting Strategies for Enabling Large Language Models to Infer Causation from Correlationcited by 7
  34. 2025LLM Cannot Discover Causality, and Should Be Restricted to Non-Decisional Support in Causal Discoverycited by 7
  35. 2025Can LLMs Reconcile Knowledge Conflicts in Counterfactual Reasoningcited by 7
  36. 2024Evaluating Interventional Reasoning Capabilities of Large Language Modelscited by 6
  37. 2025Agentic LLM Framework for Adaptive Decision Discoursecited by 6
  38. 2025Unveiling and Causalizing CoT: A Causal Pespectivecited by 6

50 most cited of 146 All 146 (JSON)