From Thinking to Output: Chain-of-Thought and Text Generation Characteristics in Reasoning Language Models

• URL: http://arxiv.org/abs/2506.21609v1
• Date: Fri, 20 Jun 2025 14:02:16 GMT
• Title: From Thinking to Output: Chain-of-Thought and Text Generation Characteristics in Reasoning Language Models
• Authors: Junhao Liu, Zhenhao Xu, Yuxin Fang, Yichuan Chen, Zuobin Ying, Wenhan Chang,
• Abstract summary: This paper proposes a novel framework for analyzing the reasoning characteristics of four cutting-edge large reasoning models.<n>A diverse dataset consists of real-world scenario-based questions covering logical deduction, causal inference, and multi-step problem-solving.<n>The research results uncover various patterns of how these models balance exploration and exploitation, deal with problems, and reach conclusions.
• Score: 10.38327947136263
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, there have been notable advancements in large language models (LLMs), demonstrating their growing abilities in complex reasoning. However, existing research largely overlooks a thorough and systematic comparison of these models' reasoning processes and outputs, particularly regarding their self-reflection pattern (also termed "Aha moment") and the interconnections across diverse domains. This paper proposes a novel framework for analyzing the reasoning characteristics of four cutting-edge large reasoning models (GPT-o1, DeepSeek-R1, Kimi-k1.5, and Grok-3) using keywords statistic and LLM-as-a-judge paradigm. Our approach connects their internal thinking processes with their final outputs. A diverse dataset consists of real-world scenario-based questions covering logical deduction, causal inference, and multi-step problem-solving. Additionally, a set of metrics is put forward to assess both the coherence of reasoning and the accuracy of the outputs. The research results uncover various patterns of how these models balance exploration and exploitation, deal with problems, and reach conclusions during the reasoning process. Through quantitative and qualitative comparisons, disparities among these models are identified in aspects such as the depth of reasoning, the reliance on intermediate steps, and the degree of similarity between their thinking processes and output patterns and those of GPT-o1. This work offers valuable insights into the trade-off between computational efficiency and reasoning robustness and provides practical recommendations for enhancing model design and evaluation in practical applications. We publicly release our project at: https://github.com/ChangWenhan/FromThinking2Output

Related papers

• Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models [49.598776427454176]
  Large Reasoning Models (LRMs) have gradually become a research hotspot due to their outstanding performance in handling complex tasks.<n>However, with the widespread application of these models, the problem of overthinking has gradually emerged.<n>Various efficient reasoning methods have been proposed, aiming to reduce the length of reasoning paths without compromising model performance and reasoning capability.
  arXiv  Detail & Related papers  (2025-08-04T06:54:31Z)
• Causal Reasoning in Pieces: Modular In-Context Learning for Causal Discovery [6.72184534513047]
  Causal inference remains a fundamental challenge for large language models.<n>Recent advances in internal reasoning with large language models have sparked interest.<n>We study causal discovery on the Corr2Cause benchmark using the OpenAI's o-series and DeepSeek-R model families.
  arXiv  Detail & Related papers  (2025-07-31T12:10:27Z)
• A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models [53.18562650350898]
  Chain-of-thought (CoT) reasoning enhances performance of large language models.<n>We present the first comprehensive study of CoT faithfulness in large vision-language models.
  arXiv  Detail & Related papers  (2025-05-29T18:55:05Z)
• PixelThink: Towards Efficient Chain-of-Pixel Reasoning [70.32510083790069]
  PixelThink is a simple yet effective scheme that integrates externally estimated task difficulty and internally measured model uncertainty.<n>It learns to compress reasoning length in accordance with scene complexity and predictive confidence.<n> Experimental results demonstrate that the proposed approach improves both reasoning efficiency and overall segmentation performance.
  arXiv  Detail & Related papers  (2025-05-29T17:55:49Z)
• Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning [21.444049407715955]
  Large Language Models (LLMs) have achieved impressive performance on complex reasoning tasks with Chain-of-Thought (CoT) prompting.<n>There has been growing research interest in latent CoT reasoning, where inference occurs within latent spaces.<n>This paper presents a comprehensive overview and analysis of this reasoning paradigm.
  arXiv  Detail & Related papers  (2025-05-22T15:26:51Z)
• Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models [54.04678363287392]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in complex tasks.<n>Recent advancements in OpenAI o1 and DeepSeek-R1 have further improved performance in System-2 reasoning domains.
  arXiv  Detail & Related papers  (2025-03-20T17:59:38Z)
• On the Reasoning Capacity of AI Models and How to Quantify It [0.0]
  Large Language Models (LLMs) have intensified the debate surrounding the fundamental nature of their reasoning capabilities.<n>While achieving high performance on benchmarks such as GPQA and MMLU, these models exhibit limitations in more complex reasoning tasks.<n>We propose a novel phenomenological approach that goes beyond traditional accuracy metrics to probe the underlying mechanisms of model behavior.
  arXiv  Detail & Related papers  (2025-01-23T16:58:18Z)
• MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs [55.20845457594977]
  Large language models (LLMs) have shown increasing capability in problem-solving and decision-making.<n>We present a process-based benchmark MR-Ben that demands a meta-reasoning skill.<n>Our meta-reasoning paradigm is especially suited for system-2 slow thinking.
  arXiv  Detail & Related papers  (2024-06-20T03:50:23Z)
• Conceptual and Unbiased Reasoning in Language Models [98.90677711523645]
  We propose a novel conceptualization framework that forces models to perform conceptual reasoning on abstract questions. We show that existing large language models fall short on conceptual reasoning, dropping 9% to 28% on various benchmarks. We then discuss how models can improve since high-level abstract reasoning is key to unbiased and generalizable decision-making.
  arXiv  Detail & Related papers  (2024-03-30T00:53:53Z)
• Comparing Inferential Strategies of Humans and Large Language Models in Deductive Reasoning [25.732397636695882]
  We show that large language models (LLMs) display reasoning patterns akin to those observed in humans. Our research demonstrates that the architecture and scale of the model significantly affect its preferred method of reasoning.
  arXiv  Detail & Related papers  (2024-02-20T12:58:14Z)
• Generation of Explanations for Logic Reasoning [0.0]
  The research is centred on employing GPT-3.5-turbo to automate the analysis of fortiori arguments. This thesis makes significant contributions to the fields of artificial intelligence and logical reasoning.
  arXiv  Detail & Related papers  (2023-11-22T15:22:04Z)

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.