# Counterfactual Causal Inference in Natural Language with Large Language Models

arXiv: https://arxiv.org/abs/2410.06392 · HTML: https://mlsanity.com/paper/2410.06392/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 62 references that are in the map.
- First posted on arXiv 8 Oct 2024.

## Builds on (most cited first, 28 of 28)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Self-Rewarding Language Models](https://mlsanity.com/paper/2401.10020/) (2024)
- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training](https://mlsanity.com/paper/2309.17179/) (2023)
- [Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks](https://mlsanity.com/paper/2307.02477/) (2023)
- [Causal Parrots: Large Language Models May Talk Causality But Are Not Causal](https://mlsanity.com/paper/2308.13067/) (2023)
- [Foundations of Structural Causal Models with Cycles and Latent Variables](https://mlsanity.com/paper/1611.06221/) (2016)
- [Causal Transformer for Estimating Counterfactual Outcomes](https://mlsanity.com/paper/2204.07258/) (2022)
- [Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement](https://mlsanity.com/paper/2310.08559/) (2023)
- [Large Language Models Are Not Strong Abstract Reasoners](https://mlsanity.com/paper/2305.19555/) (2023)
- [Efficient Causal Graph Discovery Using Large Language Models](https://mlsanity.com/paper/2402.01207/) (2024)
- [Causal Inference with Large Language Model: A Survey](https://mlsanity.com/paper/2409.09822/) (2024)
- [Causal Inference Through the Structural Causal Marginal Problem](https://mlsanity.com/paper/2202.01300/) (2022)
- [LLMs Are Prone to Fallacies in Causal Inference](https://mlsanity.com/paper/2406.12158/) (2024)
- [End-To-End Causal Effect Estimation from Unstructured Natural Language Data](https://mlsanity.com/paper/2407.07018/) (2024)
- [ROCK: Causal Inference Principles for Reasoning about Commonsense Causality](https://mlsanity.com/paper/2202.00436/) (2022)
- [Causality extraction from medical text using Large Language Models (LLMs)](https://mlsanity.com/paper/2407.10020/) (2024)
- [Detecting Emerging Technologies and their Evolution using Deep Learning and Weak Signal Analysis](https://mlsanity.com/paper/2205.05449/) (2022)

## Built on by (most cited first, 7 of 7)

- [Simulating Society Requires Simulating Thought](https://mlsanity.com/paper/2506.06958/) (2025)
- [Simulating the Unseen: Crash Prediction Must Learn from What Did Not Happen](https://mlsanity.com/paper/2505.21743/) (2025)
- [What if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual Conditions](https://mlsanity.com/paper/2605.14422/) (2026)
- [Personalized Causal Graph Reasoning for LLMs: An Implementation for Dietary Recommendations](https://mlsanity.com/paper/2503.00134/) (2025)
- [Causal Cartographer: From Mapping to Reasoning Over Counterfactual Worlds](https://mlsanity.com/paper/2505.14396/) (2025)
- [Compressed Causal Reasoning: Quantization and GraphRAG Effects on Interventional and Counterfactual Accuracy](https://mlsanity.com/paper/2512.13725/) (2025)
- [Causal-Audit: Explicit and Auditable Graph-based Reasoning via Target-Aware Causal Chain Construction](https://mlsanity.com/paper/2607.15281/) (2026)

## Abstract (arXiv)

Causal structure discovery methods are commonly applied to structured data where the causal variables are known and where statistical testing can be used to assess the causal relationships. By contrast, recovering a causal structure from unstructured natural language data such as news articles contains numerous challenges due to the absence of known variables or counterfactual data to estimate the causal links. Large Language Models (LLMs) have shown promising results in this direction but also exhibit limitations. This work investigates LLM's abilities to build causal graphs from text documents and perform counterfactual causal inference. We propose an end-to-end causal structure discovery and causal inference method from natural language: we first use an LLM to extract the instantiated causal variables from text data and build a causal graph. We merge causal graphs from multiple data sources to represent the most exhaustive set of causes possible. We then conduct counterfactual inference on the estimated graph. The causal graph conditioning allows reduction of LLM biases and better represents the causal estimands. We use our method to show that the limitations of LLMs in counterfactual causal reasoning come from prediction errors and propose directions to mitigate them. We demonstrate the applicability of our method on real-world news articles.