# Failure Modes of LLMs for Causal Reasoning on Narratives

arXiv: https://arxiv.org/abs/2410.23884 · HTML: https://mlsanity.com/paper/2410.23884/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Causal reasoning in LLMs, one of 17 directions in LLM reasoning.
- Builds on 26 of its 46 references that are in the map.
- First posted on arXiv 31 Oct 2024.

## Placed in

- LLM reasoning / [Causal reasoning in LLMs](https://mlsanity.com/lr/causal-reasoning-in-llms/)

## Builds on (most cited first, 26 of 26)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [Training Language Models to Self-Correct via Reinforcement Learning](https://mlsanity.com/paper/2409.12917/) (2024)
- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts](https://mlsanity.com/paper/2305.13300/) (2023)
- [Hurdles to Progress in Long-form Question Answering](https://mlsanity.com/paper/2103.06332/) (2021)
- [Causal Parrots: Large Language Models May Talk Causality But Are Not Causal](https://mlsanity.com/paper/2308.13067/) (2023)
- [Can Large Language Models Infer Causation from Correlation?](https://mlsanity.com/paper/2306.05836/) (2023)
- [Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models](https://mlsanity.com/paper/2402.14409/) (2024)
- [Is ChatGPT a Good Causal Reasoner? A Comprehensive Evaluation](https://mlsanity.com/paper/2305.07375/) (2023)
- [Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Models](https://mlsanity.com/paper/2406.02061/) (2024)
- [Understanding Causality with Large Language Models: Feasibility and Opportunities](https://mlsanity.com/paper/2304.05524/) (2023)
- [Automated Storytelling via Causal, Commonsense Plot Ordering](https://mlsanity.com/paper/2009.00829/) (2020)
- [CRASS: A Novel Data Set and Benchmark to Test Counterfactual Reasoning of Large Language Models](https://mlsanity.com/paper/2112.11941/) (2021)
- [The Causal News Corpus: Annotating Causal Relations in Event Sentences from News](https://mlsanity.com/paper/2204.11714/) (2022)
- [Cause and Effect: Can Large Language Models Truly Understand Causality?](https://mlsanity.com/paper/2402.18139/) (2024)
- [LLMs Are Prone to Fallacies in Causal Inference](https://mlsanity.com/paper/2406.12158/) (2024)
- [HypoGen: Hyperbole Generation with Commonsense and Counterfactual Knowledge](https://mlsanity.com/paper/2109.05097/) (2021)
- [COLA: Contextualized Commonsense Causal Reasoning from the Causal Inference Perspective](https://mlsanity.com/paper/2305.05191/) (2023)
- [WikiWhy: Answering and Explaining Cause-and-Effect Questions](https://mlsanity.com/paper/2210.12152/) (2022)
- [rmC small IS2: A Simplified Commonsense Inference Evaluation for Story Prose](https://mlsanity.com/paper/2202.07880/) (2022)

## Built on by (most cited first, 12 of 12)

- [SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planning](https://mlsanity.com/paper/2503.11951/) (2025)
- [Large Language Model Reasoning Failures](https://mlsanity.com/paper/2602.06176/) (2026)
- [MultiHoax: A Dataset of Multi-hop False-Premise Questions](https://mlsanity.com/paper/2506.00264/) (2025)
- [Can LLMs Reconcile Knowledge Conflicts in Counterfactual Reasoning](https://mlsanity.com/paper/2506.15732/) (2025)
- [Automated Penetration Testing with LLM Agents and Classical Planning](https://mlsanity.com/paper/2512.11143/) (2025)
- [Can Large Language Models Infer Causal Relationships from Real-World Text?](https://mlsanity.com/paper/2505.18931/) (2025)
- [Student Guides Teacher: Weak-to-Strong Inference via Spectral Orthogonal Exploration](https://mlsanity.com/paper/2601.06160/) (2026)
- [LogiStory: A Logic-Aware Framework for Multi-Image Story Visualization](https://mlsanity.com/paper/2603.28082/) (2026)
- [Why LLMs Fail at Causal Discovery and How Interventional Agents Escape](https://mlsanity.com/paper/2605.27567/) (2026)
- [Compressed Causal Reasoning: Quantization and GraphRAG Effects on Interventional and Counterfactual Accuracy](https://mlsanity.com/paper/2512.13725/) (2025)
- [The Illusion of textitWhat If: Evaluating the Breakdown of Counterfactual Reasoning in LLMs](https://mlsanity.com/paper/2608.27953/) (2026)
- [From Anomalies to Failures: Constructing Causal Error Graphs for Agentic Trace Diagnosis](https://mlsanity.com/paper/2609.32514/) (2026)

## Abstract (arXiv)

The ability to robustly identify causal relationships is essential for autonomous decision-making and adaptation to novel scenarios. However, accurately inferring causal structure requires integrating both world knowledge and abstract logical reasoning. In this work, we investigate the interaction between these two capabilities through the representative task of causal reasoning over narratives. Through controlled synthetic, semi-synthetic, and real-world experiments, we find that state-of-the-art large language models (LLMs) often rely on superficial heuristics -- for example, inferring causality from event order or recalling memorized world knowledge without attending to context. Furthermore, we show that simple reformulations of the task can elicit more robust reasoning behavior. Our evaluation spans a range of causal structures, from linear chains to complex graphs involving colliders and forks. These findings uncover systematic patterns in how LLMs perform causal reasoning and lay the groundwork for developing methods that better align LLM behavior with principled causal inference.