顺序迭代推理比并行多链更高效，精度最高提升46.7%。
The Sequential Edge: Inverse-Entropy Voting Beats Parallel Self-Consistency at Matched Compute
- 用序列迭代方式逐步优化推理链，取代并行多链并行
- 在5个模型、3个基准上，95.6%配置下准确率优于并行法，最高提46.7%
- 提出无训练的逆熵投票法，适合追求高精度的推理场景
我们重新审视语言模型推理中的测试时扩展策略，核心问题是：在相同计算预算下，是采用多个独立链并行执行，还是减少链数但通过序列迭代逐步优化？通过对5个顶尖开源模型和3个高难度推理基准的全面评估，我们发现序列扩展（链式迭代优化）在95.6%的配置中持续优于主流的并行自一致性方法，准确率最高提升46.7%。此外，我们提出一种无需训练的逆熵加权投票方法，根据推理链的逆熵对答案加权，显著提升序列扩展的成功率，超越并行多数投票，确立其为最优测试时扩展策略。研究挑战了自2022年Wang等提出的自一致性解码以来长期主导的并行推理范式，将序列精炼定位为现代大模型推理的稳健默认方案，亟需重构推理优化方法论。
原文摘要 · Abstract (English)
We revisit test-time scaling for language model reasoning and ask a fundamental question: at equal token budget and compute, is it better to run multiple independent chains in parallel, or to run fewer chains that iteratively refine through sequential steps? Through comprehensive evaluation across 5 state-of-the-art open source models and 3 challenging reasoning benchmarks, we find that sequential scaling where chains explicitly build upon previous attempts consistently outperforms the dominant parallel self-consistency paradigm in 95.6% of configurations with gains in accuracy upto 46.7%. Further, we introduce inverse-entropy weighted voting, a novel training-free method to further boost the accuracy of sequential scaling. By weighing answers in proportion to the inverse entropy of their reasoning chains, we increase our success rate over parallel majority and establish it as the optimal test-time scaling strategy. Our findings fundamentally challenge the parallel reasoning orthodoxy that has dominated test-time scaling since Wang et al.'s self-consistency decoding (Wang et al., 2022), positioning sequential refinement as the robust default for modern LLM reasoning and necessitating a paradigm shift in how we approach inference-time optimization.
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。