mlsanityData to 7 Oct 2026

Prompting Strategies for Enabling Large Language Models to Infer Causation from Correlation

arXiv 2412.13952 ↗First posted 18 Dec 2024cs.CL cs.AI cs.LGcited by 7

On the map: LLM reasoning → Causal reasoning in LLMs

Abstract (arXiv)

The reasoning abilities of Large Language Models (LLMs) are attracting increasing attention. In this work, we focus on causal reasoning and address the task of establishing causal relationships based on correlation information, a highly challenging problem on which several LLMs have shown poor performance. We introduce a prompting strategy for this problem that breaks the original task into fixed subquestions, with each subquestion corresponding to one step of a formal causal discovery algorithm, the PC algorithm. The proposed prompting strategy, PC-SubQ, guides the LLM to follow these algorithmic steps, by sequentially prompting it with one subquestion at a time, augmenting the next subquestion's prompt with the answer to the previous one(s). We evaluate our approach on an existing causal benchmark, Corr2Cause: our experiments indicate a performance improvement across five LLMs when comparing PC-SubQ to baseline prompting strategies. Results are robust to causal query perturbations, when modifying the variable names or paraphrasing the expressions.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Placed in Causal reasoning in LLMs, one of 17 directions in LLM reasoning. Builds on 31 of its 39 references that are in the map. First posted on arXiv 18 Dec 2024.

Builds on

31 of 39 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023CLadder: Assessing Causal Reasoning in Language Models7 Dec
  2. 2023Causal Reasoning and Large Language Models: Opening a New Frontier for Causality28 Apr

Other references · 29

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  5. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  6. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  7. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  8. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,199
  9. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 871
  10. 2022Towards Reasoning in Large Language Models: A Surveycited by 593
  11. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 554
  12. 2013Causal Discovery with Continuous Additive Noise Modelscited by 252
17 more
  1. 2022Reasoning with Language Model Prompting: A Surveycited by 251
  2. 2023Causal Parrots: Large Language Models May Talk Causality But Are Not Causalcited by 146
  3. 2023Can Large Language Models Infer Causation from Correlation?cited by 142
  4. 2022Teaching Algorithmic Reasoning via In-context Learningcited by 111
  5. 2022The CLRS Algorithmic Reasoning Benchmarkcited by 103
  6. 2022Successive Prompting for Decomposing Complex Questionscited by 94
  7. 2023Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Modelscited by 92
  8. 2013Learning Equivalence Classes of Bayesian Networks Structurescited by 75
  9. 2023Can large language models build causal graphs?cited by 72
  10. 2023Causal Discovery with Language Models as Imperfect Expertscited by 62
  11. 2023Understanding Causality with Large Language Models: Feasibility and Opportunitiescited by 53
  12. 2024Efficient Causal Graph Discovery Using Large Language Modelscited by 51
  13. 2023Causal Order: The Key to Leveraging Imperfect Experts in Causal Inferencecited by 46
  14. 2023Causal-Discovery Performance of ChatGPT in the context of Neuropathic Pain Diagnosiscited by 36
  15. 2022Can Foundation Models Talk Causality?cited by 30
  16. 2024The CLRS-Text Algorithmic Reasoning Language Benchmarkcited by 28
  17. 2024Large Language Models for Constrained-Based Causal Discoverycited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 5.

7 papers.

  1. 2025Causal Reasoning in Pieces: Modular In-Context Learning for Causal Discoverycited by 3
  2. 2025Structured Thinking Matters: Improving LLMs Generalization in Causal Inference Taskscited by 2
  3. 2026ANCHOR: Abductive Network Construction with Hierarchical Orchestration for Reliable Probability Inference in Large Language Modelscited by 1
  4. 2026Why LLMs Fail at Causal Discovery and How Interventional Agents Escapecited by 1
  5. 2026When Do We Need LLMs? A Diagnostic for Language-Driven Banditscited by 0
  6. 2026CausalGuard: Conformal Inference under Graph Uncertaintycited by 0
  7. 2026Externalized CPDAG Summaries Improve LLM Causal Deductioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Enhancing Causal Reasoning in Large Language Models: A Causal Attribution Model for Precision Fine-Tuning
  2. 2024CausalBN-Bench: A Comprehensive Benchmark for Causal Learning Capability of LLMs
  3. 2024Large Language Models and Causal Inference in Collaboration: A Survey
  4. 2024A Critical Review of Causal Reasoning Benchmarks for Large Language Models
  5. 2026Debiasing Large Language Models via Adaptive Causal Prompting with Sketch-of-Thought
  6. 2024C2P: Featuring Large Language Models with Causal Reasoning
  7. 2023LLM4Causal: Democratized Causal Tools for Everyone via Large Language Model
  8. 2024Eliciting Causal Abilities in Large Language Models for Reasoning Tasks