让大模型自己验证纠错，高效提升推理能力
SETS: Leveraging Self-Verification and Self-Correction for Improved Test-Time Scaling
- 融合并行采样与串行修正，用模型自检自纠
- 在数学、编程等任务上显著超越现有方法
- 无需训练，适合部署在任意大模型上
近期大语言模型在测试时计算方面的进展，为复杂推理任务的性能提升带来了新机遇。然而，现有扩展方法存在明显局限：并行方法如重复采样效率低且易饱和，而串行方法如SELF-REFINE在少数轮次后难以继续改进。尽管结合两者有潜力，但当前方法需依赖微调的奖励与修订模型。本文提出自增强测试时扩展（SETS），一种简单而有效的方法，通过策略性结合并行与串行技术，并充分利用大模型的自我改进能力，克服上述局限。SETS利用大模型固有的自验证与自纠正能力，将采样、验证与修正统一于单一框架中，实现无需任何模型训练的高效可扩展测试时计算，显著提升复杂任务表现。在涵盖规划、推理、数学与编码的多个挑战性基准上的全面实验表明，SETS不仅取得显著性能提升，且展现出更优的测试时扩展特性。
原文摘要 · Abstract (English)
Recent advancements in Large Language Models (LLMs) have created new opportunities to enhance performance on complex reasoning tasks by leveraging test-time computation. However, existing scaling methods have key limitations: parallel methods like repeated sampling are often inefficient and quickly saturate, while sequential methods like SELF-REFINE struggle to improve after a few rounds. Although combining these approaches shows promise, current methods require fine-tuned reward and revision models. This paper proposes Self-Enhanced Test-Time Scaling (SETS), a simple yet effective approach that overcomes these limitations by strategically combining parallel and sequential techniques and fully leveraging LLMs' self-improvement abilities. SETS exploits the inherent self-verification and self-correction capabilities of LLMs, unifying sampling, verification, and correction within a single framework. This facilitates efficient and scalable test-time computation for enhanced performance on complex tasks without any model training. Our comprehensive experimental results on challenging benchmarks spanning planning, reasoning, math, and coding demonstrate that SETS achieves significant performance improvements and more advantageous test-time scaling behavior than the alternatives.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。