# What Kind of Reasoning (if any) is an LLM actually doing? On the Stochastic Nature and Abductive Appearance of Large Language Models

arXiv: https://arxiv.org/abs/2512.10080 · HTML: https://mlsanity.com/paper/2512.10080/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 1 of its 7 references that are in the map.
- First posted on arXiv 10 Dec 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 1 of 1)

- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)

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

- [AILS-NTUA at SemEval-2026 Task 12: Graph-Based Retrieval and Reflective Prompting for Abductive Event Reasoning](https://mlsanity.com/paper/2603.04319/) (2026)
- [LLMs Don't Pay for the Jump](https://mlsanity.com/paper/2608.14397/) (2026)
- [Assessing mentalization in humans and large language models](https://mlsanity.com/paper/2608.26291/) (2026)
- [Opaque Epistemic Mediation: How LLM Deployment Configurations Shape the Validation of Pseudo-Science](https://mlsanity.com/paper/2607.22513/) (2026)

## Abstract (arXiv)

This article looks at how reasoning works in current Large Language Models (LLMs) that function using the token-completion method. It examines their stochastic nature and their similarity to human abductive reasoning. The argument is that these LLMs create text based on learned patterns rather than performing actual abductive reasoning. When their output seems abductive, this is largely because they are trained on human-generated texts that include reasoning structures. Examples are used to show how LLMs can produce plausible ideas, mimic commonsense reasoning, and give explanatory answers without being grounded in truth, semantics, verification, or understanding, and without performing any real abductive reasoning. This dual nature, where the models have a stochastic base but appear abductive in use, has important consequences for how LLMs are evaluated and applied. They can assist with generating ideas and supporting human thinking, but their outputs must be critically assessed because they cannot identify truth or verify their explanations. The article concludes by addressing five objections to these points, noting some limitations in the analysis, and offering an overall evaluation.