CoT is Not True Reasoning, It Is Just a Tight Constraint to Imitate: A Theory Perspective

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shao, Jintian, Cheng, Yiming
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915331737387008
author Shao, Jintian
Cheng, Yiming
author_facet Shao, Jintian
Cheng, Yiming
contents Chain-of-Thought (CoT) prompting has demonstrably enhanced the performance of Large Language Models on tasks requiring multi-step inference. This success has led to widespread claims of emergent reasoning capabilities in these models. In this paper, we present a theoretical counter-perspective: Chain-of-Thought (CoT) does not elicit genuine, abstract reasoning. Instead, we argue that Chain-of-Thought functions as a powerful structural constraint that guides Large Language Models to imitate the form of reasoning. By forcing the generation of intermediate steps, Chain-of-Thought leverages the model immense capacity for sequence prediction and pattern matching, effectively constraining its output to sequences that resemble coherent thought processes. Chain-of-Thought (CoT) prompting has demonstrably enhanced the performance of Large Language Models on tasks requiring multi-step inference. This success has led to widespread claims of emergent reasoning capabilities in these models. In this paper, we present a theoretical counter-perspective: Chain-of-Thought (CoT) does not elicit genuine, abstract reasoning. Instead, we argue that Chain-of-Thought functions as a powerful structural constraint that guides Large Language Models to imitate the form of reasoning. By forcing the generation of intermediate steps, Chain-of-Thought leverages the model immense capacity for sequence prediction and pattern matching, effectively constraining its output to sequences that resemble coherent thought processes.
format Preprint
id arxiv_https___arxiv_org_abs_2506_02878
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CoT is Not True Reasoning, It Is Just a Tight Constraint to Imitate: A Theory Perspective
Shao, Jintian
Cheng, Yiming
Computation and Language
Artificial Intelligence
Chain-of-Thought (CoT) prompting has demonstrably enhanced the performance of Large Language Models on tasks requiring multi-step inference. This success has led to widespread claims of emergent reasoning capabilities in these models. In this paper, we present a theoretical counter-perspective: Chain-of-Thought (CoT) does not elicit genuine, abstract reasoning. Instead, we argue that Chain-of-Thought functions as a powerful structural constraint that guides Large Language Models to imitate the form of reasoning. By forcing the generation of intermediate steps, Chain-of-Thought leverages the model immense capacity for sequence prediction and pattern matching, effectively constraining its output to sequences that resemble coherent thought processes. Chain-of-Thought (CoT) prompting has demonstrably enhanced the performance of Large Language Models on tasks requiring multi-step inference. This success has led to widespread claims of emergent reasoning capabilities in these models. In this paper, we present a theoretical counter-perspective: Chain-of-Thought (CoT) does not elicit genuine, abstract reasoning. Instead, we argue that Chain-of-Thought functions as a powerful structural constraint that guides Large Language Models to imitate the form of reasoning. By forcing the generation of intermediate steps, Chain-of-Thought leverages the model immense capacity for sequence prediction and pattern matching, effectively constraining its output to sequences that resemble coherent thought processes.
title CoT is Not True Reasoning, It Is Just a Tight Constraint to Imitate: A Theory Perspective
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2506.02878