mlsanityData to 14 Oct 2026

Understanding Causality with Large Language Models: Feasibility and Opportunities

arXiv 2304.05524 ↗First posted 11 Apr 2023cs.LG cs.CLcited by 53

Not on the map. Why?

Cited by 21 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We assess the ability of large language models (LLMs) to answer causal questions by analyzing their strengths and weaknesses against three types of causal question. We believe that current LLMs can answer causal questions with existing causal knowledge as combined domain experts. However, they are not yet able to provide satisfactory answers for discovering new knowledge or for high-stakes decision-making tasks with high precision. We discuss possible future directions and opportunities, such as enabling explicit and implicit causal modules as well as deep causal-aware LLMs. These will not only enable LLMs to answer many different types of causal questions for greater impact but also enable LLMs to be more trustworthy and efficient in general.

Key facts. Cited by 53 papers in the map (data through 14 Oct 2026). Builds on 11 of its 26 references that are in the map. First posted on arXiv 11 Apr 2023.

Builds on

11 of 26 references.

References · 11

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  5. 2022LaMDA: Language Models for Dialog Applicationscited by 1,220
  6. 2023How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detectioncited by 481
  7. 2022Complexity-Based Prompting for Multi-Step Reasoningcited by 388
  8. 2022Deep End-to-end Causal Inferencecited by 95
  9. 2017Causal Structure Learningcited by 84
  10. 2021Shaking the foundations: delusions in sequence models for interaction and controlcited by 62
  11. 2022Toward Self-learning End-to-End Task-Oriented Dialog Systemscited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 15; 2024: 23; 2025: 12; 2026: 3.

53 papers.

Sort:

By area:

  1. 2023Causal Reasoning and Large Language Models: Opening a New Frontier for Causalitycited by 353
  2. 2023CLadder: Assessing Causal Reasoning in Language Modelscited by 107
  3. 2024DPLM-2: A Multimodal Diffusion Protein Language Modelcited by 64
  4. 2023Integrating Large Language Model for Improved Causal Discoverycited by 54
  5. 2023Large Language Models are Temporal and Causal Reasoners for Video Question Answeringcited by 51
  6. 2023Diffusion Language Models Can Perform Many Tasks with Scaling and Instruction-Finetuningcited by 39
  7. 2025Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?cited by 38
  8. 2023The Mystery of In-Context Learning: A Comprehensive Survey on Interpretation and Analysiscited by 34
  9. 2024The Essential Role of Causality in Foundation World Models for Embodied AIcited by 32
  10. 2023CRAB: Assessing the Strength of Causal Relationships Between Real-world Eventscited by 28
  11. 2024Causality for Large Language Modelscited by 25
  12. 2024Cause and Effect: Can Large Language Models Truly Understand Causality?cited by 23
38 more
  1. 2024Prompting Fairness: Integrating Causality to Debias Large Language Modelscited by 21
  2. 2025CounterBench: Evaluating and Improving Counterfactual Reasoning in Large Language Modelscited by 21
  3. 2024Causal Evaluation of Language Modelscited by 18
  4. 2023Towards Causal Foundation Model: on Duality between Causal Inference and Attentioncited by 17
  5. 2023An Interdisciplinary Outlook on Large Language Models for Scientific Researchcited by 15
  6. 2023Zero-shot Causal Graph Extrapolation from Text via LLMscited by 15
  7. 2023GPT-Based Models Meet Simulation: How to Efficiently Use Large-Scale Pre-Trained Language Models Across Simulation Taskscited by 14
  8. 2024A Critical Review of Causal Reasoning Benchmarks for Large Language Modelscited by 14
  9. 2024Reasoning Elicitation in Language Models via Counterfactual Feedbackcited by 14
  10. 2024Limits of Transformer Language Models on Learning to Compose Algorithmscited by 13
  11. 2024Cloud Atlas: Efficient Fault Localization for Cloud Systems using Language Models and Causal Insightcited by 12
  12. 2024Failure Modes of LLMs for Causal Reasoning on Narrativescited by 12
  13. 2025Can Large Language Models Help Experimental Design for Causal Discovery?cited by 11
  14. 2024Discovering and Reasoning of Causality in the Hidden World with Large Language Modelscited by 10
  15. 2024CELLO: Causal Evaluation of Large Vision-Language Modelscited by 10
  16. 2023LLM4Causal: Democratized Causal Tools for Everyone via Large Language Modelcited by 9
  17. 2024CHECKWHY: Causal Fact Verification via Argument Structurecited by 9
  18. 2023Applying Large Language Models for Causal Structure Learning in Non Small Cell Lung Cancercited by 8
  19. 2025LLM Cannot Discover Causality, and Should Be Restricted to Non-Decisional Support in Causal Discoverycited by 8
  20. 2024Prompting Strategies for Enabling Large Language Models to Infer Causation from Correlationcited by 7
  21. 2025CausalVLBench: Benchmarking Visual Causal Reasoning in Large Vision-Language Modelscited by 7
  22. 2025Can LLMs Leverage Observational Data? Towards Data-Driven Causal Discovery with LLMscited by 5
  23. 2026Diagnosing and Mitigating Sycophancy and Skepticism in LLM Causal Judgmentcited by 5
  24. 2024Estimating Causal Effects of Text Interventions Leveraging LLMscited by 4
  25. 2023Learned Causal Method Predictioncited by 3
  26. 2024Prompting or Fine-tuning? Exploring Large Language Models for Causal Graph Validationcited by 3
  27. 2024Using GPT-4 to guide causal machine learningcited by 3
  28. 2024Knowledge Graph Structure as Prompt: Improving Small Language Models Capabilities for Knowledge-based Causal Discoverycited by 3
  29. 2023Building Resilient SMEs: Harnessing Large Language Models for Cyber Security in Australiacited by 2
  30. 2024The Implicit Bias of Heterogeneity towards Invariance: A Study of Multi-Environment Matrix Sensingcited by 2
  31. 2024Do LLMs Have the Generalization Ability in Conducting Causal Inference?cited by 2
  32. 2025BiasCause: Evaluate Socially Biased Causal Reasoning of Large Language Modelscited by 2
  33. 2025Causal Distillation: Transferring Structured Explanations from Large to Compact Language Modelscited by 2
  34. 2025LLM-Driven Treatment Effect Estimation Under Inference Time Text Confoundingcited by 2
  35. 2024Latent Causal Probing: A Formal Perspective on Probing with Causal Models of Datacited by 1
  36. 2025CRAwDAD: Causal Reasoning Augmentation with Dual-Agent Debatecited by 1
  37. 2026Linear-LLM-SCM: Benchmarking LLMs for Coefficient Elicitation in Linear-Gaussian Causal Modelscited by 1
  38. 2026Why LLMs Fail at Causal Discovery and How Interventional Agents Escapecited by 1

50 most cited of 53 All 53 (JSON)