Coarse-to-Fine Process Reward Modeling for Mathematical Reasoning
- URL: http://arxiv.org/abs/2501.13622v3
- Date: Tue, 18 Feb 2025 13:05:36 GMT
- Title: Coarse-to-Fine Process Reward Modeling for Mathematical Reasoning
- Authors: Yulan Hu, Ge Chen, Jinman Zhao, Sheng Ouyang, Yong Liu,
- Abstract summary: The Process Reward Model (PRM) plays a crucial role in mathematical reasoning tasks, requiring high-quality supervised process data.
We observe that reasoning steps generated by Large Language Models (LLMs) often fail to exhibit strictly incremental information, leading to redundancy.
We propose CFPRM, a simple yet effective coarse-to-fine strategy for detecting redundant steps.
- Score: 11.15613673478208
- License:
- Abstract: The Process Reward Model (PRM) plays a crucial role in mathematical reasoning tasks, requiring high-quality supervised process data. However, we observe that reasoning steps generated by Large Language Models (LLMs) often fail to exhibit strictly incremental information, leading to redundancy that can hinder effective reasoning. To address this issue, we propose CFPRM, a simple yet effective coarse-to-fine strategy. Instead of focusing on the detection of redundant steps, our approach first establishes a coarse-grained window to merge adjacent reasoning steps into unified, holistic steps. The window size is then progressively reduced to extract fine-grained reasoning steps, enabling data collection at multiple granularities for training. By leveraging this hierarchical refinement process, CFPRM mitigates redundancy while preserving essential fine-grained knowledge. Extensive experiments on two reasoning datasets across three loss criteria validate the CFPRM's effectiveness and versatility.
Related papers
- 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) - 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) - ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding [25.329712997545794]
We propose Retrieval-Augmented Reasoning through Trustworthy Process Rewarding (ReARTeR)
ReARTeR enhances RAG systems' reasoning capabilities through post-training and test-time scaling.
Experimental results on multi-step reasoning benchmarks demonstrate significant improvements.
arXiv Detail & Related papers (2025-01-14T05:56:26Z) - Reinforcing Thinking through Reasoning-Enhanced Reward Models [6.636512424910708]
Large Language Models (LLMs) exhibit great potential in complex multi-step reasoning through inference-time thinking.
LLMs struggle with deciding when to stop thinking due to limited self-awareness about their knowledge boundaries.
This work addresses these challenges by distilling the LLM's own reasoning processes into synthetic behavioral data.
arXiv Detail & Related papers (2024-12-31T04:50:15Z) - Closer Look at Efficient Inference Methods: A Survey of Speculative Decoding [1.3479499607624648]
Speculative decoding addresses bottleneck by introducing a two-stage framework: drafting and verification.
A smaller, efficient model generates a preliminary draft, which is then refined by a larger, more sophisticated model.
This paper provides a comprehensive survey of speculative decoding methods, categorizing them into draft-centric and model-centric approaches.
arXiv Detail & Related papers (2024-11-20T09:46:30Z) - 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) - 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) - Counterfactual Learning of Stochastic Policies with Continuous Actions:
from Models to Offline Evaluation [41.21447375318793]
We introduce a modelling strategy based on a joint kernel embedding of contexts and actions.
We empirically show that the optimization aspect of counterfactual learning is important.
We propose an evaluation protocol for offline policies in real-world logged systems.
arXiv Detail & Related papers (2020-04-22T07:42:30Z)
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.