Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs
Test-time scaling (TTS) has gained widespread attention for enhancing LLM reasoning. Existing approaches such as Best-of-N and majority voting are limited as their performance depends on the quality of candidate responses, making them unable to produce a correct solution when all candidates are incorrect. Parallel self-refinement, generating multiple candidates and synthesizing a refined answer conditioned on them, offers a promising alternative, but the underlying mechanism driving its effectiveness remains obscure. To bridge this gap in understanding, we introduce a new metric, the Refinement Gap, designed to quantify the relative improvement of self-refinement beyond majority voting. We show that the Refinement Gap exhibits a clear scaling trend with model size and is only weakly correlated with the base capability. Based on this discovery, we propose Generative Self-Refinement (GSR), a parallel test-time scaling framework that transfers the refinement policy from larger teacher models with higher refinement gap into smaller students. Crucially, GSR jointly trains a single model to generate strong candidates and refine a better final answer based on these candidates. Experimental results demonstrate that our method achieves state-of-the-art performance across five mathematical benchmarks over other parallel aggregation methods, while the learned refinement skill transfers across multiple model scales and families and exhibits robust generalization to an out-of-distribution domain.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
CoRefine: Confidence-Guided Self-Refinement for Adaptive Test-Time Compute
Large Language Models (LLMs) often rely on test-time scaling via parallel decoding (for example, 512 samples) to boost reasoning accuracy, but this incurs substantial compute. We introduce CoRefine, a confidence-guided s…
The ART of LLM Refinement: Ask, Refine, and Trust
In recent years, Large Language Models (LLMs) have demonstrated remarkable generative abilities, but can they judge the quality of their own generations? A popular concept, referred to as self-refinement, postulates that…
Arithmetic ReasoningGSM8KQuestion AnsweringStrategyQARefineRL: Advancing Competitive Programming with Self-Refinement Reinforcement Learning
While large language models (LLMs) have demonstrated strong performance on complex reasoning tasks such as competitive programming (CP), existing methods predominantly focus on single-attempt settings, overlooking their …
Reinforcement LearningSSR: Socratic Self-Refine for Large Language Model Reasoning
Large Language Models (LLMs) have demonstrated remarkable reasoning abilities, yet existing test-time frameworks often rely on coarse self-verification and self-correction, limiting their effectiveness on complex tasks. …
MC-NEST -- Enhancing Mathematical Reasoning in Large Language Models with a Monte Carlo Nash Equilibrium Self-Refine Tree
Mathematical reasoning has proven to be a critical yet challenging task for large language models (LLMs), as they often struggle with complex multi-step problems. To address these limitations, we introduce the Monte Carl…
Decision MakingMathematical Reasoning