mlsanityData to 13 Oct 2026

Are UFOs Driving Innovation? The Illusion of Causality in Large Language Models

arXiv 2410.11684 ↗First posted 15 Oct 2024cs.AI cs.CL cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Illusions of causality occur when people develop the belief that there is a causal connection between two variables with no supporting evidence. This cognitive bias has been proposed to underlie many societal problems including social prejudice, stereotype formation, misinformation and superstitious thinking. In this research we investigate whether large language models develop the illusion of causality in real-world settings. We evaluated and compared news headlines generated by GPT-4o-Mini, Claude-3.5-Sonnet, and Gemini-1.5-Pro to determine whether the models incorrectly framed correlations as causal relationships. In order to also measure sycophantic behavior, which occurs when a model aligns with a user's beliefs in order to look favorable even if it is not objectively correct, we additionally incorporated the bias into the prompts, observing if this manipulation increases the likelihood of the models exhibiting the illusion of causality. We found that Claude-3.5-Sonnet is the model that presents the lowest degree of causal illusion aligned with experiments on Correlation-to-Causation Exaggeration in human-written press releases. On the other hand, our findings suggest that while mimicry sycophancy increases the likelihood of causal illusions in these models, especially in GPT-4o-Mini, Claude-3.5-Sonnet remains the most robust against this cognitive bias.

Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Builds on 12 of its 25 references that are in the map. First posted on arXiv 15 Oct 2024.

Builds on

12 of 25 references.

References · 12

  1. 2023Towards Understanding Sycophancy in Language Modelscited by 1,018
  2. 2023Causal Reasoning and Large Language Models: Opening a New Frontier for Causalitycited by 352
  3. 2023Simple synthetic data reduces sycophancy in large language modelscited by 185
  4. 2022Thinking Fast and Slow in Large Language Modelscited by 136
  5. 2023CLadder: Assessing Causal Reasoning in Language Modelscited by 105
  6. 2024Cognitive Bias in Decision-Making with LLMscited by 105
  7. 2023Is ChatGPT a Good Causal Reasoner? A Comprehensive Evaluationcited by 69
  8. 2023MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Taskscited by 44
  9. 2024Chaos with Keywords: Exposing Large Language Models Sycophantic Hallucination to Misleading Keywords and Evaluating Defense Strategiescited by 10
  10. 2019Illusion of Causality in Visualized Datacited by 8
  11. 2024Evaluating Interventional Reasoning Capabilities of Large Language Modelscited by 6
  12. 2024Balancing Rigor and Utility: Mitigating Cognitive Biases in Large Language Models for Multiple-Choice Questionscited by 2

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Do Large Language Models Show Biases in Causal Learning? Insights from Contingency Judgmentcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026Illusory Pattern Perception Drives Spurious Inference in Large Language Models
  2. 2025Do Large Language Models Reason Causally Like Us? Even Better?
  3. 2026Do LLMs Share Human-Like Biases? Causal Reasoning Under Prior Knowledge, Irrelevant Context, and Varying Compute Budgets
  4. 2025Hallucinate Less by Thinking More: Aspect-Based Causal Abstention for Large Language Models
  5. 2023Can Large Language Models Infer Causation from Correlation?
  6. 2025BiasCause: Evaluate Socially Biased Causal Reasoning of Large Language Models
  7. 2026Diagnosing and Mitigating Sycophancy and Skepticism in LLM Causal Judgment
  8. 2025Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?