用多候选联合验证提升大模型推理准确率与速度
Parallel Test-Time Scaling with Multi-Sequence Verifiers
- 基于全部候选解联合判断每条答案对错，避免孤立评分
- 在数学推理任务上将64选1准确率提升6%，延迟减半
- 适合追求高精度低延迟推理的AI应用开发者
并行测试时扩展通过为单一问题生成多个候选解来提升大语言模型性能，但面临两大瓶颈：从候选集中准确选出正确答案，以及生成大量完整解带来的高推理延迟。本文认为这两个问题本质均源于验证器校准不足，校准良好的验证器能提升答案选择效果，并支持早期停止策略降低延迟。现有非生成式验证器仅孤立评估每个候选，忽略候选集间的上下文信息。为此，提出轻量级多序列验证器（MSV），其在给定全部采样候选集的条件下预测每条候选的正确性。实验表明，MSV显著改善验证器校准度，直接提升64选1选择性能，且在早期停止设置下，以不到一半的延迟达到基线相同准确率。在多个挑战性数学推理基准上验证有效。
原文摘要 · Abstract (English)
Parallel test-time scaling, which generates multiple candidate solutions for a single problem, is a powerful technique for improving large language model performance. However, it is hindered by two key bottlenecks: accurately selecting the correct solution from the candidate pool, and the high inference latency from generating many full solutions. We argue that both challenges are fundamentally linked to verifier calibration, as a well-calibrated verifier improves answer selection and enables early-stopping strategies to reduce latency. However, existing non-generative verifiers are limited as they score each candidate in isolation, overlooking rich contextual information across the set of candidates. To address this, we introduce the Multi-Sequence Verifier (MSV), a lightweight verifier that predicts each candidate's correctness conditioned on the full sampled set. MSV achieves improved calibration, which directly enhances best-of-N selection performance and empowers a novel early-stopping framework. Across challenging mathematical reasoning benchmarks, MSV improves best-of-64 accuracy by up to 6\% relative to strong baselines, and in the early-stopping setting reaches the same accuracy as baselines with less than half the latency.
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。