The CoT Encyclopedia: Analyzing, Predicting, and Controlling how a Reasoning Model will Think

• URL: http://arxiv.org/abs/2505.10185v1
• Date: Thu, 15 May 2025 11:31:02 GMT
• Title: The CoT Encyclopedia: Analyzing, Predicting, and Controlling how a Reasoning Model will Think
• Authors: Seongyun Lee, Seungone Kim, Minju Seo, Yongrae Jo, Dongyoung Go, Hyeonbin Hwang, Jinho Park, Xiang Yue, Sean Welleck, Graham Neubig, Moontae Lee, Minjoon Seo,
• Abstract summary: We introduce the CoT Encyclopedia, a framework for analyzing and steering model reasoning.<n>Our method automatically extracts diverse reasoning criteria from model-generated CoTs.<n>We show that this framework produces more interpretable and comprehensive analyses than existing methods.
• Score: 81.38614558541772
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Long chain-of-thought (CoT) is an essential ingredient in effective usage of modern large language models, but our understanding of the reasoning strategies underlying these capabilities remains limited. While some prior works have attempted to categorize CoTs using predefined strategy types, such approaches are constrained by human intuition and fail to capture the full diversity of model behaviors. In this work, we introduce the CoT Encyclopedia, a bottom-up framework for analyzing and steering model reasoning. Our method automatically extracts diverse reasoning criteria from model-generated CoTs, embeds them into a semantic space, clusters them into representative categories, and derives contrastive rubrics to interpret reasoning behavior. Human evaluations show that this framework produces more interpretable and comprehensive analyses than existing methods. Moreover, we demonstrate that this understanding enables performance gains: we can predict which strategy a model is likely to use and guide it toward more effective alternatives. Finally, we provide practical insights, such as that training data format (e.g., free-form vs. multiple-choice) has a far greater impact on reasoning behavior than data domain, underscoring the importance of format-aware model design.

Related papers

• Relative Overfitting and Accept-Reject Framework [5.465098504510676]
  We propose an ensemble framework that governs how models are segmented to ensure performance improvement.<n>We detail the patterns of this framework within the domain of NLP and briefly describe its to other fields, such as computer vision (CV) and AI for science.
  arXiv  Detail & Related papers  (2025-05-12T17:36:14Z)
• Model Steering: Learning with a Reference Model Improves Generalization Bounds and Scaling Laws [52.10468229008941]
  This paper formalizes an emerging learning paradigm that uses a trained model as a reference to guide and enhance the training of a target model through strategic data selection or weighting.<n>We provide theoretical insights into why this approach improves generalization and data efficiency compared to training without a reference model.<n>Building on these insights, we introduce a novel method for Contrastive Language-Image Pretraining with a reference model, termed DRRho-CLIP.
  arXiv  Detail & Related papers  (2025-05-10T16:55:03Z)
• How to Probe: Simple Yet Effective Techniques for Improving Post-hoc Explanations [69.72654127617058]
  Post-hoc importance attribution methods are a popular tool for "explaining" Deep Neural Networks (DNNs)<n>In this work we bring forward empirical evidence that challenges this very notion.<n>We discover a strong dependency on and demonstrate that the training details of a pre-trained model's classification layer play a crucial role.
  arXiv  Detail & Related papers  (2025-03-01T22:25:11Z)
• 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)
• When factorization meets argumentation: towards argumentative explanations [0.0]
  We propose a novel model that combines factorization-based methods with argumentation frameworks (AFs) Our framework seamlessly incorporates side information, such as user contexts, leading to more accurate predictions.
  arXiv  Detail & Related papers  (2024-05-13T19:16:28Z)
• Exploring the Trade-off Between Model Performance and Explanation Plausibility of Text Classifiers Using Human Rationales [3.242050660144211]
  Saliency post-hoc explainability methods are important tools for understanding increasingly complex NLP models. We present a methodology for incorporating rationales, which are text annotations explaining human decisions, into text classification models.
  arXiv  Detail & Related papers  (2024-04-03T22:39:33Z)
• Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanations [13.60538902487872]
  We present a novel post-hoc concept-based XAI framework that conveys besides instance-wise (local) also class-wise (global) decision-making strategies via prototypes. We demonstrate the effectiveness of our approach in identifying out-of-distribution samples, spurious model behavior and data quality issues across three datasets.
  arXiv  Detail & Related papers  (2023-11-28T10:53:26Z)
• Studying How to Efficiently and Effectively Guide Models with Explanations [52.498055901649025]
  'Model guidance' is the idea of regularizing the models' explanations to ensure that they are "right for the right reasons" We conduct an in-depth evaluation across various loss functions, attribution methods, models, and 'guidance depths' on the PASCAL VOC 2007 and MS COCO 2014 datasets. Specifically, we guide the models via bounding box annotations, which are much cheaper to obtain than the commonly used segmentation masks.
  arXiv  Detail & Related papers  (2023-03-21T15:34:50Z)
• MACE: An Efficient Model-Agnostic Framework for Counterfactual Explanation [132.77005365032468]
  We propose a novel framework of Model-Agnostic Counterfactual Explanation (MACE) In our MACE approach, we propose a novel RL-based method for finding good counterfactual examples and a gradient-less descent method for improving proximity. Experiments on public datasets validate the effectiveness with better validity, sparsity and proximity.
  arXiv  Detail & Related papers  (2022-05-31T04:57:06Z)
• Attentional Prototype Inference for Few-Shot Segmentation [128.45753577331422]
  We propose attentional prototype inference (API), a probabilistic latent variable framework for few-shot segmentation. We define a global latent variable to represent the prototype of each object category, which we model as a probabilistic distribution. We conduct extensive experiments on four benchmarks, where our proposal obtains at least competitive and often better performance than state-of-the-art prototype-based methods.
  arXiv  Detail & Related papers  (2021-05-14T06:58:44Z)

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.