Why Does Your CoT Prompt (Not) Work? Theoretical Analysis of Prompt Space Complexity, its Interaction with Answer Space During CoT Reasoning with LLMs: A Recurrent Perspective

• URL: http://arxiv.org/abs/2503.10084v1
• Date: Thu, 13 Mar 2025 06:11:10 GMT
• Title: Why Does Your CoT Prompt (Not) Work? Theoretical Analysis of Prompt Space Complexity, its Interaction with Answer Space During CoT Reasoning with LLMs: A Recurrent Perspective
• Authors: Xiang Zhang, Juntai Cao, Jiaqi Wei, Chenyu You, Dujian Ding,
• Abstract summary: Chain-of-Thought (CoT) prompting has emerged as a practical solution to the limitations of Large Language Models (LLMs)<n>This paper provides a rigorous theoretical analysis of the complexity and interplay between two crucial spaces: the prompt space and the answer space.<n>We show that sometimes human supervision is critical for efficiently navigating the prompt space.
• Score: 15.941209553757274
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite the remarkable successes of Large Language Models (LLMs), their fundamental Transformer architecture possesses inherent theoretical limitations that restrict their capability to handle reasoning tasks with increasing computational complexity. Chain-of-Thought (CoT) prompting has emerged as a practical solution, supported by several theoretical studies. However, current CoT-based methods (including ToT, GoT, etc.) generally adopt a "one-prompt-fits-all" strategy, using fixed templates (e.g., "think step by step") across diverse reasoning tasks. This method forces models to navigate an extremely complex prompt space to identify effective reasoning paths. The current prompt designing research are also heavily relying on trial-and-error rather than theoretically informed guidance. In this paper, we provide a rigorous theoretical analysis of the complexity and interplay between two crucial spaces: the prompt space (the space of potential prompt structures) and the answer space (the space of reasoning solutions generated by LLMs) in CoT reasoning. We demonstrate how reliance on a single universal prompt (e.g. think step by step) can negatively impact the theoretical computability of LLMs, illustrating that prompt complexity directly influences the structure and effectiveness of the navigation in answer space. Our analysis highlights that sometimes human supervision is critical for efficiently navigating the prompt space. We theoretically and empirically show that task-specific prompting significantly outperforms unsupervised prompt generation, emphasizing the necessity of thoughtful human guidance in CoT prompting.

Related papers

• Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1) [66.51642638034822]
  Reasoning is central to human intelligence, enabling structured problem-solving across diverse tasks. Recent advances in large language models (LLMs) have greatly enhanced their reasoning abilities in arithmetic, commonsense, and symbolic domains. This paper offers a concise yet insightful overview of reasoning techniques in both textual and multimodal LLMs.
  arXiv  Detail & Related papers  (2025-04-04T04:04:56Z)
• When More is Less: Understanding Chain-of-Thought Length in LLMs [53.77747102201451]
  Chain-of-thought (CoT) reasoning enhances the multi-step reasoning capabilities of large language models (LLMs)<n>However, for most models and tasks, does an increase in CoT length consistently lead to improved reasoning accuracy?<n>In this paper, we observe a nuanced relationship: as the number of reasoning steps increases, performance initially improves but eventually decreases.
  arXiv  Detail & Related papers  (2025-02-11T05:28:59Z)
• Supervised Chain of Thought [5.389461633686935]
  Chain of Thought (CoT) prompting offers a promising approach to solving complex reasoning tasks. One-prompt-for-all approach poses significant challenges for models to generate the correct reasoning steps. We show how task-specific supervision is essential for navigating the prompt space accurately and achieving optimal performance.
  arXiv  Detail & Related papers  (2024-10-18T06:25:27Z)
• Make LLMs better zero-shot reasoners: Structure-orientated autonomous reasoning [52.83539473110143]
  We introduce a novel structure-oriented analysis method to help Large Language Models (LLMs) better understand a question. To further improve the reliability in complex question-answering tasks, we propose a multi-agent reasoning system, Structure-oriented Autonomous Reasoning Agents (SARA) Extensive experiments verify the effectiveness of the proposed reasoning system. Surprisingly, in some cases, the system even surpasses few-shot methods.
  arXiv  Detail & Related papers  (2024-10-18T05:30:33Z)
• Instance-adaptive Zero-shot Chain-of-Thought Prompting [32.700073951068575]
  Zero-shot Chain-of-Thought (CoT) prompting emerges as a simple and effective strategy for enhancing the performance of large language models (LLMs) in real-world reasoning tasks. This work introduces an instance-adaptive prompting algorithm as an alternative zero-shot CoT reasoning scheme by adaptively differentiating good and bad prompts.
  arXiv  Detail & Related papers  (2024-09-30T16:00:34Z)
• On the Empirical Complexity of Reasoning and Planning in LLMs [29.588100727466976]
  Chain-of-thought (CoT), tree-of-thought (ToT), and related techniques work surprisingly well in practice for some complex reasoning tasks with Large Language Models (LLMs) This work seeks the underlying reasons by conducting experimental case studies and linking the performance benefits to well-established sample and computational complexity principles in machine learning.
  arXiv  Detail & Related papers  (2024-04-17T03:34:27Z)
• Large Language Models as an Indirect Reasoner: Contrapositive and Contradiction for Automated Reasoning [74.90592233107712]
  We propose a Direct-Indirect Reasoning (DIR) method, which considers Direct Reasoning (DR) and Indirect Reasoning (IR) as multiple parallel reasoning paths that are merged to derive the final answer.<n>Our DIR method is simple yet effective and can be straightforwardly integrated with existing variants of CoT methods.
  arXiv  Detail & Related papers  (2024-02-06T03:41:12Z)
• Parrot Mind: Towards Explaining the Complex Task Reasoning of Pretrained Large Language Models with Template-Content Structure [66.33623392497599]
  We show that a structure called template-content structure (T-C structure) can reduce the possible space from exponential level to linear level. We demonstrate that models can achieve task composition, further reducing the space needed to learn from linear to logarithmic.
  arXiv  Detail & Related papers  (2023-10-09T06:57:45Z)
• Prompt Space Optimizing Few-shot Reasoning Success with Large Language Models [7.453926835095568]
  Prompt engineering enables large language models (LLMs) to excel in various tasks, such as arithmetic reasoning, question answering, summarization, relation extraction, machine translation, and sentiment analysis. Current approaches lack a solid mathematical solution for determining optimal prompts. Our methodology utilizes text embeddings to obtain basis vectors by matrix decomposition, and then constructs a space for representing all prompts.
  arXiv  Detail & Related papers  (2023-06-06T15:43:16Z)
• Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective [39.47116013338394]
  Chain-of-Thought prompting (CoT) can dramatically improve the performance of Large Language Models (LLMs) We show that CoT can handle a general class of decision-making problems known as Dynamic Programming.
  arXiv  Detail & Related papers  (2023-05-24T17:59:21Z)
• Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters [82.84696222087396]
  Chain-of-Thought (CoT) prompting can dramatically improve the multi-step reasoning abilities of large language models (LLMs) We show that CoT reasoning is possible even with invalid demonstrations.
  arXiv  Detail & Related papers  (2022-12-20T05:20:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.