mlsanityData to 14 Oct 2026

Causal Reasoning and Large Language Models: Opening a New Frontier for Causality

arXiv 2305.00050 ↗First posted 28 Apr 2023cs.AI cs.CL cs.CYcited by 353

On the map: LLM reasoning → Causal reasoning in LLMs

Abstract (arXiv)

The causal capabilities of large language models (LLMs) are a matter of significant debate, with critical implications for the use of LLMs in societally impactful domains such as medicine, science, law, and policy. We conduct a "behavorial" study of LLMs to benchmark their capability in generating causal arguments. Across a wide range of tasks, we find that LLMs can generate text corresponding to correct causal arguments with high probability, surpassing the best-performing existing methods. Algorithms based on GPT-3.5 and 4 outperform existing algorithms on a pairwise causal discovery task (97%, 13 points gain), counterfactual reasoning task (92%, 20 points gain) and event causality (86% accuracy in determining necessary and sufficient causes in vignettes). We perform robustness checks across tasks and show that the capabilities cannot be explained by dataset memorization alone, especially since LLMs generalize to novel datasets that were created after the training cutoff date. That said, LLMs exhibit unpredictable failure modes, and we discuss the kinds of errors that may be improved and what are the fundamental limits of LLM-based answers. Overall, by operating on the text metadata, LLMs bring capabilities so far understood to be restricted to humans, such as using collected knowledge to generate causal graphs or identifying background causal context from natural language. As a result, LLMs may be used by human domain experts to save effort in setting up a causal analysis, one of the biggest impediments to the widespread adoption of causal methods. Given that LLMs ignore the actual data, our results also point to a fruitful research direction of developing algorithms that combine LLMs with existing causal techniques. Code and datasets are available at https://github.com/py-why/pywhy-llm.

Key facts. Cited by 353 papers in the map (data through 14 Oct 2026). Placed in Causal reasoning in LLMs, one of 17 directions in LLM reasoning. Builds on 34 of its 128 references that are in the map. First posted on arXiv 28 Apr 2023.

Builds on

34 of 128 references.

References · 34

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  4. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  5. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  6. 2022Emergent Abilities of Large Language Modelscited by 2,512
  7. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,998
  8. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,807
  9. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,470
  10. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,045
  11. 2022Quantifying Memorization Across Neural Language Modelscited by 763
  12. 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 752
22 more
  1. 2023AGIEval: A Human-Centric Benchmark for Evaluating Foundation Modelscited by 716
  2. 2023Capabilities of GPT-4 on Medical Challenge Problemscited by 638
  3. 2019DAG-GNN: DAG Structure Learning with Graph Neural Networkscited by 331
  4. 2020A Survey of the State of Explainable AI for Natural Language Processingcited by 206
  5. 2023Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4cited by 202
  6. 2023Can large language models build causal graphs?cited by 73
  7. 2022LMPriors: Pre-Trained Language Models as Task-Specific Priorscited by 56
  8. 2023Understanding Causality with Large Language Models: Feasibility and Opportunitiescited by 53
  9. 2021Unsuitability of NOTEARS for Causal Graph Discoverycited by 47
  10. 2021Why did the distribution change?cited by 37
  11. 2023Causal-Discovery Performance of ChatGPT in the context of Neuropathic Pain Diagnosiscited by 36
  12. 2021CRASS: A Novel Data Set and Benchmark to Test Counterfactual Reasoning of Large Language Modelscited by 34
  13. 2019Neuropathic Pain Diagnosis Simulator for Causal Discovery Algorithm Evaluationcited by 32
  14. 2021Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processingcited by 30
  15. 2022Can Foundation Models Talk Causality?cited by 30
  16. 2017Telling Cause from Effect using MDL-based Local and Global Regressioncited by 21
  17. 2021DoWhy: Addressing Challenges in Expressing and Validating Causal Assumptionscited by 20
  18. 2020Review of The Book of Why: The New Science of Cause and Effectcited by 19
  19. 2020Causal Mosaic: Cause-Effect Inference via Nonlinear ICA and Ensemble Methodcited by 16
  20. 2022Towards Understanding How Machines Can Learn Causal Overhypothesescited by 14
  21. 2013Graded Causation and Defaultscited by 13
  22. 2022The Counterfactual-Shapley Value: Attributing Change in System Metricscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 56; 2024: 103; 2025: 92; 2026: 102.

353 papers.

Sort:

By area:

  1. 2025Gemma 3 Technical Reportcited by 1,824
  2. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 401
  3. 2023Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Taskscited by 246
  4. 2024Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMscited by 229
  5. 2024MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Makingcited by 163
  6. 2023In-Context Impersonation Reveals Large Language Models' Strengths and Biasescited by 155
  7. 2023Causal Parrots: Large Language Models May Talk Causality But Are Not Causalcited by 150
  8. 2023Can Large Language Models Infer Causation from Correlation?cited by 146
  9. 2025BIG-Bench Extra Hardcited by 125
  10. 2023ReviewerGPT? An Exploratory Study on Using Large Language Models for Paper Reviewingcited by 122
  11. 2024Evaluating the World Model Implicit in a Generative Modelcited by 113
  12. 2023CLadder: Assessing Causal Reasoning in Language Modelscited by 107
38 more
  1. 2024Robust agents learn causal world modelscited by 81
  2. 2024Can large language models explore in-context?cited by 76
  3. 2023Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generationcited by 74
  4. 2023GPTEval: A Survey on Assessments of ChatGPT and GPT-4cited by 73
  5. 2023Is ChatGPT a Good Causal Reasoner? A Comprehensive Evaluationcited by 69
  6. 2023Causal Discovery with Language Models as Imperfect Expertscited by 64
  7. 2024Are LLMs Capable of Data-based Statistical and Causal Reasoning? Benchmarking Advanced Quantitative Reasoning with Datacited by 63
  8. 2023Integrating Large Language Model for Improved Causal Discoverycited by 54
  9. 2023Large Language Models Are Not Strong Abstract Reasonerscited by 53
  10. 2023Do LLM Agents Exhibit Social Behavior?cited by 53
  11. 2024Efficient Causal Graph Discovery Using Large Language Modelscited by 53
  12. 2026MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agentscited by 52
  13. 2023Large Language Models are Temporal and Causal Reasoners for Video Question Answeringcited by 51
  14. 2024ReXTime: A Benchmark Suite for Reasoning-Across-Time in Videoscited by 51
  15. 2024Large Language Models and Cognitive Science: A Comprehensive Review of Similarities, Differences, and Challengescited by 49
  16. 2023Causal Order: The Key to Leveraging Imperfect Experts in Causal Inferencecited by 48
  17. 2023Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactualscited by 44
  18. 2023MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Taskscited by 44
  19. 2024Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causalitycited by 42
  20. 2023Vamos: Versatile Action Models for Video Understandingcited by 40
  21. 2025Exploring the Impact of Temperature on Large Language Models:Hot or Cold?cited by 40
  22. 2023Diffusion Language Models Can Perform Many Tasks with Scaling and Instruction-Finetuningcited by 39
  23. 2025Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?cited by 38
  24. 2023The Mystery of In-Context Learning: A Comprehensive Survey on Interpretation and Analysiscited by 34
  25. 2024How Likely Do LLMs with CoT Mimic Human Reasoning?cited by 34
  26. 2024Integrating Large Language Models in Causal Discovery: A Statistical Causal Approachcited by 32
  27. 2024The Essential Role of Causality in Foundation World Models for Embodied AIcited by 32
  28. 2024Causal Inference with Large Language Model: A Surveycited by 32
  29. 2023Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectivescited by 30
  30. 2024ALCM: Autonomous LLM-Augmented Causal Discovery Frameworkcited by 29
  31. 2023CRAB: Assessing the Strength of Causal Relationships Between Real-world Eventscited by 28
  32. 2024Large Language Models and Causal Inference in Collaboration: A Surveycited by 26
  33. 2024MedFuzz: Exploring the Robustness of Large Language Models in Medical Question Answeringcited by 26
  34. 2024Multi-Agent Causal Discovery Using Large Language Modelscited by 26
  35. 2024Large Language Models for Causal Discovery: Current Landscape and Future Directionscited by 25
  36. 2024Understanding Long Videos with Multimodal Language Modelscited by 25
  37. 2024Causality for Large Language Modelscited by 25
  38. 2023Inductive reasoning in humans and large language modelscited by 24

50 most cited of 353 All 353 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024CausalBN-Bench: A Comprehensive Benchmark for Causal Learning Capability of LLMs
  2. 2025Causality for Natural Language Processing
  3. 2026METER: Evaluating Multi-Level Contextual Causal Reasoning in Large Language Models
  4. 2024CARL-GT: Evaluating Causal Reasoning Capabilities of Large Language Models
  5. 2026Uncovering Hidden Correctness in LLM Causal Reasoning via Symbolic Verification
  6. 2025Causal Reasoning in Pieces: Modular In-Context Learning for Causal Discovery
  7. 2026Do LLMs Share Human-Like Biases? Causal Reasoning Under Prior Knowledge, Irrelevant Context, and Varying Compute Budgets
  8. 2025BiasCause: Evaluate Socially Biased Causal Reasoning of Large Language Models