# Ice Cream Doesn't Cause Drowning: Benchmarking LLMs Against Statistical Pitfalls in Causal Inference

arXiv: https://arxiv.org/abs/2505.13770 · HTML: https://mlsanity.com/paper/2505.13770/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 48 references that are in the map.
- First posted on arXiv 19 May 2025.

## Builds on (most cited first, 19 of 19)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Solving Quantitative Reasoning Problems with Language Models](https://mlsanity.com/paper/2206.14858/) (2022)
- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [Causal Parrots: Large Language Models May Talk Causality But Are Not Causal](https://mlsanity.com/paper/2308.13067/) (2023)
- [CLadder: Assessing Causal Reasoning in Language Models](https://mlsanity.com/paper/2312.04350/) (2023)
- [Counterfactual Story Reasoning and Generation](https://mlsanity.com/paper/1909.04076/) (2019)
- [Causal Discovery with Language Models as Imperfect Experts](https://mlsanity.com/paper/2307.02390/) (2023)
- [Are LLMs Capable of Data-based Statistical and Causal Reasoning? Benchmarking Advanced Quantitative Reasoning with Data](https://mlsanity.com/paper/2402.17644/) (2024)
- [Can Foundation Models Talk Causality?](https://mlsanity.com/paper/2206.10591/) (2022)
- [Instrumental Variables Estimation with Some Invalid Instruments and its Application to Mendelian Randomization](https://mlsanity.com/paper/1401.5755/) (2014)
- [CausalBN-Bench: A Comprehensive Benchmark for Causal Learning Capability of LLMs](https://mlsanity.com/paper/2404.06349/) (2024)
- [End-To-End Causal Effect Estimation from Unstructured Natural Language Data](https://mlsanity.com/paper/2407.07018/) (2024)
- [Doubly Debiased Lasso: High-Dimensional Inference under Hidden Confounding](https://mlsanity.com/paper/2004.03758/) (2020)
- [Nonlinear Causal Discovery with Confounders](https://mlsanity.com/paper/2302.03178/) (2023)
- [Discovery and inference of a causal network with hidden confounding](https://mlsanity.com/paper/2309.09420/) (2023)
- [Enhancing Causal Effect Estimation with Diffusion-Generated Data](https://mlsanity.com/paper/2504.03630/) (2025)
- [A nonparametric doubly robust test for a continuous treatment effect](https://mlsanity.com/paper/2202.03369/) (2022)
- [Drift to Remember](https://mlsanity.com/paper/2409.13997/) (2024)

## Built on by (most cited first, 6 of 6)

- [LIBERTy: A Causal Framework for Benchmarking Concept-Based Explanations of LLMs with Structural Counterfactuals](https://mlsanity.com/paper/2601.10700/) (2026)
- [CausalDS: Benchmarking Causal Reasoning in Data-Science Agents](https://mlsanity.com/paper/2607.08093/) (2026)
- [Towards a Universal Causal Reasoner](https://mlsanity.com/paper/2605.24873/) (2026)
- [Automated Synthesis and Adversarial Validation of Executable Causal Research Pipelines](https://mlsanity.com/paper/2607.21173/) (2026)
- [Evidence-Type Competition: When Can Interventional Data Teach Language Models Causal Direction?](https://mlsanity.com/paper/2607.29484/) (2026)
- [ACED-Bench: Evaluating How LLM Agents Acquire and Act on Causal Evidence](https://mlsanity.com/paper/2610.14381/) (2026)

## Abstract (arXiv)

Reliable causal inference is essential for making decisions in high-stakes areas like medicine, economics, and public policy. However, it remains unclear whether large language models (LLMs) can handle rigorous and trustworthy statistical causal inference. Current benchmarks usually involve simplified tasks. For example, these tasks might only ask LLMs to identify semantic causal relationships or draw conclusions directly from raw data. As a result, models may overlook important statistical pitfalls, such as Simpson's paradox or selection bias. This oversight limits the applicability of LLMs in the real world. To address these limitations, we propose CausalPitfalls, a comprehensive benchmark designed to rigorously evaluate the capability of LLMs in overcoming common causal inference pitfalls. Our benchmark features structured challenges across multiple difficulty levels, each paired with grading rubrics. This approach allows us to quantitatively measure both causal reasoning capabilities and the reliability of LLMs' responses. We evaluate models using two protocols: (1) direct prompting, which assesses intrinsic causal reasoning, and (2) code-assisted prompting, where models generate executable code for explicit statistical analysis. Additionally, we validate the effectiveness of this judge by comparing its scoring with assessments from human experts. Our results reveal significant limitations in current LLMs when performing statistical causal inference. The CausalPitfalls benchmark provides essential guidance and quantitative metrics to advance the development of trustworthy causal reasoning systems.