PSPO*: An Effective Process-supervised Policy Optimization for Reasoning Alignment

• URL: http://arxiv.org/abs/2411.11681v2
• Date: Sat, 23 Nov 2024 15:52:38 GMT
• Title: PSPO*: An Effective Process-supervised Policy Optimization for Reasoning Alignment
• Authors: Jiawei Li, Xinyue Liang, Yizhe Yang, Chong Feng, Yang Gao,
• Abstract summary: We develop PSPO-WRS, which considers the number of reasoning steps in determining reward scores and utilizes an adjusted Weibull distribution for nonlinear reward shaping. Experimental results on six mathematical reasoning datasets demonstrate that PSPO-WRS consistently outperforms current mainstream models.
• Score: 20.053439187190914
• License:
• Abstract: Process supervision enhances the performance of large language models in reasoning tasks by providing feedback at each step of chain-of-thought reasoning. However, due to the lack of effective process supervision methods, even advanced large language models are prone to logical errors and redundant reasoning. We claim that the effectiveness of process supervision significantly depends on both the accuracy and the length of reasoning chains. Moreover, we identify that these factors exhibit a nonlinear relationship with the overall reward score of the reasoning process. Inspired by these insights, we propose a novel process supervision paradigm, PSPO*, which systematically outlines the workflow from reward model training to policy optimization, and highlights the importance of nonlinear rewards in process supervision. Based on PSPO*, we develop the PSPO-WRS, which considers the number of reasoning steps in determining reward scores and utilizes an adjusted Weibull distribution for nonlinear reward shaping. Experimental results on six mathematical reasoning datasets demonstrate that PSPO-WRS consistently outperforms current mainstream models.

Related papers

• Step-by-Step Reasoning for Math Problems via Twisted Sequential Monte Carlo [55.452453947359736]
  We introduce a novel verification method based on Twisted Sequential Monte Carlo (TSMC) We apply TSMC to Large Language Models by estimating the expected future rewards at partial solutions. This approach results in a more straightforward training target that eliminates the need for step-wise human annotations.
  arXiv  Detail & Related papers  (2024-10-02T18:17:54Z)
• Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging Tasks [68.49251303172674]
  State-of-the-art large language models (LLMs) exhibit impressive problem-solving capabilities but may struggle with complex reasoning and factual correctness. Existing methods harness the strengths of chain-of-thought and retrieval-augmented generation (RAG) to decompose a complex problem into simpler steps and apply retrieval to improve factual correctness. We introduce Critic-guided planning with Retrieval-augmentation, CR-Planner, a novel framework that leverages fine-tuned critic models to guide both reasoning and retrieval processes through planning.
  arXiv  Detail & Related papers  (2024-10-02T11:26:02Z)
• Learning Off-policy with Model-based Intrinsic Motivation For Active Online Exploration [15.463313629574111]
  This paper investigates how to achieve sample-efficient exploration in continuous control tasks. We introduce an RL algorithm that incorporates a predictive model and off-policy learning elements. We derive an intrinsic reward without incurring parameters overhead.
  arXiv  Detail & Related papers  (2024-03-31T11:39:11Z)
• Learning Logic Specifications for Policy Guidance in POMDPs: an Inductive Logic Programming Approach [57.788675205519986]
  We learn high-quality traces from POMDP executions generated by any solver. We exploit data- and time-efficient Indu Logic Programming (ILP) to generate interpretable belief-based policy specifications. We show that learneds expressed in Answer Set Programming (ASP) yield performance superior to neural networks and similar to optimal handcrafted task-specifics within lower computational time.
  arXiv  Detail & Related papers  (2024-02-29T15:36:01Z)
• 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)
• Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizing [61.98556945939045]
  We propose a framework to learn planning-based reasoning through Direct Preference Optimization (DPO) on collected trajectories. Our results on challenging logical reasoning benchmarks demonstrate the effectiveness of our learning framework.
  arXiv  Detail & Related papers  (2024-02-01T15:18:33Z)
• 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)
• Making Linear MDPs Practical via Contrastive Representation Learning [101.75885788118131]
  It is common to address the curse of dimensionality in Markov decision processes (MDPs) by exploiting low-rank representations. We consider an alternative definition of linear MDPs that automatically ensures normalization while allowing efficient representation learning. We demonstrate superior performance over existing state-of-the-art model-based and model-free algorithms on several benchmarks.
  arXiv  Detail & Related papers  (2022-07-14T18:18:02Z)
• Distributional Reinforcement Learning for Scheduling of (Bio)chemical Production Processes [0.0]
  Reinforcement Learning (RL) has recently received significant attention from the process systems engineering and control communities. We present a RL methodology to address precedence and disjunctive constraints as commonly imposed on production scheduling problems.
  arXiv  Detail & Related papers  (2022-03-01T17:25:40Z)

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.