DialCoT Meets PPO: Decomposing and Exploring Reasoning Paths in Smaller Language Models

• URL: http://arxiv.org/abs/2310.05074v3
• Date: Mon, 23 Oct 2023 09:38:01 GMT
• Title: DialCoT Meets PPO: Decomposing and Exploring Reasoning Paths in Smaller Language Models
• Authors: Chengcheng Han, Xiaowei Du, Che Zhang, Yixin Lian, Xiang Li, Ming Gao, Baoyuan Wang
• Abstract summary: Chain-of-Thought (CoT) prompting has proven to be effective in enhancing the reasoning capabilities of Large Language Models (LLMs) with at least 100 billion parameters. We introduce Dialogue-guided Chain-of-Thought (DialCoT) which employs a dialogue format to generate intermediate reasoning steps, guiding the model toward the final answer.
• Score: 18.96271708412086
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Chain-of-Thought (CoT) prompting has proven to be effective in enhancing the reasoning capabilities of Large Language Models (LLMs) with at least 100 billion parameters. However, it is ineffective or even detrimental when applied to reasoning tasks in Smaller Language Models (SLMs) with less than 10 billion parameters. To address this limitation, we introduce Dialogue-guided Chain-of-Thought (DialCoT) which employs a dialogue format to generate intermediate reasoning steps, guiding the model toward the final answer. Additionally, we optimize the model's reasoning path selection using the Proximal Policy Optimization (PPO) algorithm, further enhancing its reasoning capabilities. Our method offers several advantages compared to previous approaches. Firstly, we transform the process of solving complex reasoning questions by breaking them down into a series of simpler sub-questions, significantly reducing the task difficulty and making it more suitable for SLMs. Secondly, we optimize the model's reasoning path selection through the PPO algorithm. We conduct comprehensive experiments on four arithmetic reasoning datasets, demonstrating that our method achieves significant performance improvements compared to state-of-the-art competitors.

Related papers

• AdaR1: From Long-CoT to Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization [86.56120216550232]
  We propose a novel two-stage framework for adaptive and efficient reasoning. First, we construct a hybrid reasoning model by merging long and short CoT models. Second, we apply bi-level preference training to guide the model to select suitable reasoning styles.
  arXiv  Detail & Related papers  (2025-04-30T14:01:45Z)
• Short-Path Prompting in LLMs: Analyzing Reasoning Instability and Solutions for Robust Performance [33.16322104912836]
  Large language models' (LLMs) reasoning is largely due to the chain-of-thought (CoT) approaches. LLMs are instruction-tuned to provide long and detailed CoT pathways when responding to reasoning-related questions. Human beings are naturally cognitive misers and will prompt language models to give rather short responses.
  arXiv  Detail & Related papers  (2025-04-13T14:12:14Z)
• Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models [54.04678363287392]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in complex tasks. 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)
• Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models [56.37421741507468]
  Chain-of-Thought (CoT) reasoning has significantly enhanced the performance of large language models (LLMs) We propose a method to identify critical reasoning steps using perplexity as a measure of their importance.
  arXiv  Detail & Related papers  (2025-02-18T20:04:51Z)
• A Comparative Study on Reasoning Patterns of OpenAI's o1 Model [69.08287909042421]
  We show that OpenAI's o1 model has achieved the best performance on most datasets. We also provide a detailed analysis on several reasoning benchmarks.
  arXiv  Detail & Related papers  (2024-10-17T15:09:03Z)
• 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)
• Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization [50.485788083202124]
  Reinforcement Learning (RL) plays a crucial role in aligning large language models with human preferences and improving their ability to perform complex tasks. We introduce Direct Q-function Optimization (DQO), which formulates the response generation process as a Markov Decision Process (MDP) and utilizes the soft actor-critic (SAC) framework to optimize a Q-function directly parameterized by the language model. Experimental results on two math problem-solving datasets, GSM8K and MATH, demonstrate that DQO outperforms previous methods, establishing it as a promising offline reinforcement learning approach for aligning language models.
  arXiv  Detail & Related papers  (2024-10-11T23:29:20Z)
• Logic Contrastive Reasoning with Lightweight Large Language Model for Math Word Problems [0.0]
  This study focuses on improving the performance of lightweight Large Language Models (LLMs) in mathematical reasoning tasks. We introduce a novel method for measuring mathematical logic similarity and design an automatic screening mechanism. By employing carefully crafted positive and negative example prompts, we guide the model towards adopting sound reasoning logic.
  arXiv  Detail & Related papers  (2024-08-29T08:26:42Z)
• Combinatorial Reasoning: Selecting Reasons in Generative AI Pipelines via Combinatorial Optimization [2.090904951468026]
  Large Language Models (LLMs) have demonstrated impressive capabilities at tasks that require human intelligence. Yet the reasoning capability of LLMs is a matter of significant debate. We introduce a framework for what we call Combinatorial Reasoning (CR), a fully-automated prompting method.
  arXiv  Detail & Related papers  (2024-06-19T16:47:44Z)
• 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. 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)
• Let's reward step by step: Step-Level reward model as the Navigators for Reasoning [64.27898739929734]
  Process-Supervised Reward Model (PRM) furnishes LLMs with step-by-step feedback during the training phase. We propose a greedy search algorithm that employs the step-level feedback from PRM to optimize the reasoning pathways explored by LLMs. To explore the versatility of our approach, we develop a novel method to automatically generate step-level reward dataset for coding tasks and observed similar improved performance in the code generation tasks.
  arXiv  Detail & Related papers  (2023-10-16T05:21:50Z)
• Guiding Language Model Reasoning with Planning Tokens [122.43639723387516]
  Large language models (LLMs) have recently attracted considerable interest for their ability to perform complex reasoning tasks. We propose a hierarchical generation scheme to encourage a more structural generation of chain-of-thought steps. Our approach requires a negligible increase in trainable parameters (0.001%) and can be applied through either full fine-tuning or a more parameter-efficient scheme.
  arXiv  Detail & Related papers  (2023-10-09T13:29:37Z)
• Thought Propagation: An Analogical Approach to Complex Reasoning with Large Language Models [62.96551299003463]
  We propose textbftextitThought Propagation (TP) to enhance the complex reasoning ability of Large Language Models. TP first prompts LLMs to propose and solve a set of analogous problems that are related to the input one. TP reuses the results of analogous problems to directly yield a new solution or derive a knowledge-intensive plan for execution to amend the initial solution obtained from scratch.
  arXiv  Detail & Related papers  (2023-10-06T01:40:09Z)
• Sci-CoT: Leveraging Large Language Models for Enhanced Knowledge Distillation in Small Models for Scientific QA [5.117094291273979]
  Large Language Models (LLMs) have shown outstanding performance across wide range of downstream tasks. We propose Sci-CoT, a two-stage framework that separates the processes of generating rationales and inferring answers. Our 80-million parameter model is able to exceed the performance of BLOOM-176B in the ARC-Easy dataset under the few shot setting.
  arXiv  Detail & Related papers  (2023-08-09T03:18:07Z)
• Complexity-Based Prompting for Multi-Step Reasoning [72.0057198610614]
  We study the task of prompting large-scale language models to perform multi-step reasoning. A central question is which reasoning examples make the most effective prompts. We propose complexity-based prompting, a simple and effective example selection scheme for multi-step reasoning.
  arXiv  Detail & Related papers  (2022-10-03T05:33:27Z)

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.