# Do Chains-of-Thoughts of Large Language Models Suffer from Hallucinations, Cognitive Biases, or Phobias in Bayesian Reasoning?

arXiv: https://arxiv.org/abs/2503.15268 · HTML: https://mlsanity.com/paper/2503.15268/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 5 of its 53 references that are in the map.
- First posted on arXiv 19 Mar 2025.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)

## Builds on (most cited first, 5 of 5)

- [Evaluating the Robustness of Analogical Reasoning in Large Language Models](https://mlsanity.com/paper/2411.14215/) (2024)
- [Thought Cloning: Learning to Think while Acting by Imitating Human Thinking](https://mlsanity.com/paper/2306.00323/) (2023)
- [Imagining and building wise machines: The centrality of AI metacognition](https://mlsanity.com/paper/2411.02478/) (2024)
- [Beyond Text-to-Text: An Overview of Multimodal and Generative Artificial Intelligence for Education Using Topic Modeling](https://mlsanity.com/paper/2409.16376/) (2024)
- [GPT-4o reads the mind in the eyes](https://mlsanity.com/paper/2410.22309/) (2024)

## Built on by (most cited first, 4 of 4)

- [Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety](https://mlsanity.com/paper/2506.05451/) (2025)
- [Reasoning Model is Stubborn: Diagnosing Instruction Overriding in Reasoning Models](https://mlsanity.com/paper/2505.17225/) (2025)
- [Uncovering Systematic Failures of LLMs in Verifying Code Against Natural Language Specifications](https://mlsanity.com/paper/2508.12358/) (2025)
- [Are LLMs Reliable Code Reviewers? Systematic Overcorrection in Requirement Conformance Judgement](https://mlsanity.com/paper/2603.00539/) (2026)

## Abstract (arXiv)

Learning to reason and carefully explain arguments is central to students' cognitive, mathematical, and computational thinking development. This is particularly challenging in problems under uncertainty and in Bayesian reasoning. With the new generation of large language models (LLMs) capable of reasoning using Chain-of-Thought (CoT), there is an excellent opportunity to learn with them as they explain their reasoning through a dialogue with their artificial internal voice. It is an engaging and excellent opportunity to learn Bayesian reasoning. Furthermore, given that different LLMs sometimes arrive at opposite solutions, CoT generates opportunities for deep learning by detailed comparisons of reasonings. However, unlike humans, we found that they do not autonomously explain using ecologically valid strategies like natural frequencies, whole objects, and embodied heuristics. This is unfortunate, as these strategies help humans avoid critical mistakes and have proven pedagogical value in Bayesian reasoning. In order to overcome these biases and aid understanding and learning, we included prompts that induce LLMs to use these strategies. We found that LLMs with CoT incorporate them but not consistently. They show persistent biases towards symbolic reasoning and avoidance or phobia of ecologically valid strategies.