A Tutorial on LLM Reasoning: Relevant Methods behind ChatGPT o1

• URL: http://arxiv.org/abs/2502.10867v1
• Date: Sat, 15 Feb 2025 17:52:11 GMT
• Title: A Tutorial on LLM Reasoning: Relevant Methods behind ChatGPT o1
• Authors: Jun Wang,
• Abstract summary: OpenAI o1 has shown that applying reinforcement learning to integrate reasoning steps directly during inference can significantly improve a model's reasoning capabilities. We present a comprehensive formulation of reasoning problems and investigate the use of both model-based and model-free approaches to better support this slow-thinking framework.
• Score: 6.527607790666018
• License:
• Abstract: OpenAI o1 has shown that applying reinforcement learning to integrate reasoning steps directly during inference can significantly improve a model's reasoning capabilities. This result is exciting as the field transitions from the conventional autoregressive method of generating answers to a more deliberate approach that models the slow-thinking process through step-by-step reasoning training. Reinforcement learning plays a key role in both the model's training and decoding processes. In this article, we present a comprehensive formulation of reasoning problems and investigate the use of both model-based and model-free approaches to better support this slow-thinking framework.

Related papers

• BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning [78.63421517563056]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks. We present a unified probabilistic framework that formalizes LLM reasoning through a novel graphical model. We introduce the Bootstrapping Reinforced Thinking Process (BRiTE) algorithm, which works in two steps.
  arXiv  Detail & Related papers  (2025-01-31T02:39:07Z)
• Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback [94.25162866972077]
  Step-KTO is a training framework that combines process-level and outcome-level binary feedback. Our experiments show that Step-KTO significantly improves both final answer accuracy and the quality of intermediate reasoning steps.
  arXiv  Detail & Related papers  (2025-01-18T15:38:03Z)
• PRefLexOR: Preference-based Recursive Language Modeling for Exploratory Optimization of Reasoning and Agentic Thinking [0.0]
  PRefLexOR combines preference optimization with concepts from Reinforcement Learning to enable models to self-teach. We focus on applications in biological materials science and demonstrate the method in a variety of case studies.
  arXiv  Detail & Related papers  (2024-10-16T08:46:26Z)
• Using Part-based Representations for Explainable Deep Reinforcement Learning [30.566205347443113]
  We propose a non-negative training approach for actor models in Deep Reinforcement Learning. We demonstrate the effectiveness of the proposed approach using the well-known Cartpole benchmark.
  arXiv  Detail & Related papers  (2024-08-21T09:21:59Z)
• SAIE Framework: Support Alone Isn't Enough -- Advancing LLM Training with Adversarial Remarks [47.609417223514605]
  This work introduces the SAIE framework, which facilitates supportive and adversarial discussions between learner and partner models. Our empirical evaluation shows that models fine-tuned with the SAIE framework outperform those trained with conventional fine-tuning approaches.
  arXiv  Detail & Related papers  (2023-11-14T12:12:25Z)
• Deep Generative Models for Decision-Making and Control [4.238809918521607]
  The dual purpose of this thesis is to study the reasons for these shortcomings and to propose solutions for the uncovered problems. We highlight how inference techniques from the contemporary generative modeling toolbox, including beam search, can be reinterpreted as viable planning strategies for reinforcement learning problems.
  arXiv  Detail & Related papers  (2023-06-15T01:54:30Z)
• Learning to Agree on Vision Attention for Visual Commonsense Reasoning [50.904275811951614]
  A VCR model aims at answering a question regarding an image, followed by the rationale prediction for the preceding answering process. Existing methods ignore the pivotal relationship between the two processes, leading to sub-optimal model performance. This paper presents a novel visual attention alignment method to efficaciously handle these two processes in a unified framework.
  arXiv  Detail & Related papers  (2023-02-04T07:02:29Z)
• When to Update Your Model: Constrained Model-based Reinforcement Learning [50.74369835934703]
  We propose a novel and general theoretical scheme for a non-decreasing performance guarantee of model-based RL (MBRL) Our follow-up derived bounds reveal the relationship between model shifts and performance improvement. A further example demonstrates that learning models from a dynamically-varying number of explorations benefit the eventual returns.
  arXiv  Detail & Related papers  (2022-10-15T17:57:43Z)
• Towards Interpretable Deep Learning Models for Knowledge Tracing [62.75876617721375]
  We propose to adopt the post-hoc method to tackle the interpretability issue for deep learning based knowledge tracing (DLKT) models. Specifically, we focus on applying the layer-wise relevance propagation (LRP) method to interpret RNN-based DLKT model. Experiment results show the feasibility using the LRP method for interpreting the DLKT model's predictions.
  arXiv  Detail & Related papers  (2020-05-13T04:03:21Z)

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.