用少量示例+测试时提示增强，显著提升大模型推理能力
Prompting Test-Time Scaling Is A Strong LLM Reasoning Data Augmentation
- 仅用90个手工示例，通过测试时提示强度变化生成多样化推理路径
- 在AIME24/25等任务上，7B和32B模型比基线提升超26%准确率
- 适合资源有限或需快速迭代的场景，无需大量标注数据
大型语言模型（LLMs）在提供思维链示例时展现出强大推理能力，但构建大规模推理数据集仍耗时费力。本文提出测试时提示增强（P-TTS），一种简单有效的推理增强策略。P-TTS仅使用90个手动筛选的推理示例，通过测试时系统性调整指令提示强度，生成多样化的推理轨迹上下文，并在此基础上对Qwen-2.5系列模型进行微调。在AIME2024 & 25、MATH500和GPQA-Diamond等多个数学推理任务上，P-TTS-7B与32B模型优于S1和S1.1（1K-shot）基线，在AIME'24上分别取得+26.66%和+30.00%的绝对准确率提升，AIME'25上分别+13.34%和+6.67%；32B模型在AIME'24和AIME'25上分别获得+23.33%和+16.63%，以及+26.63%和+3.33%的提升，且在MATH500和GPQA-Diamond上表现相当或更优。P-TTS还显著提升零样本泛化能力，在高考、考研、奥数题、AMC23、小学数学和Minerva等跨域推理基准上均表现良好。分析表明，测试时缩放有效探索了推理模式的潜在空间，以极低标注成本释放了大模型的推理潜力。
原文摘要 · Abstract (English)
Large language models (LLMs) have demonstrated impressive reasoning capabilities when provided with chain-of-thought exemplars, but curating large reasoning datasets remains laborious and resource-intensive. In this work, we introduce Prompting Test-Time Scaling (P-TTS), a simple yet effective inference-time data augmentation strategy for enhancing LLM reasoning through finetuning. Rather than collecting thousands or even millions of examples, P-TTS leverages a small pool of only 90 manually selected reasoning instances and systematically varies exemplar augmentation through principled instruction prompting intensities at test time to synthesize diverse reasoning trajectory contexts. Then we finetune the various sizes of Qwen-2.5 models on P-TTS data. Across a suite of mathematical reasoning AIME2024 & 25, MATH500, and GPQA-Diamond, our P-TTS-7B and 32B models outperform the prior competitive baselines like S1 and S1.1 (1K-shot), achieving absolute accuracy gains of +26.66% and +30.00% on AIME'24 (7B), and +13.34% and +6.67% on AIME'25 (7B); P-TTS-32B yields gains of +23.33% and +16.63% on AIME'24, and +26.63% and +3.33% on AIME'25 (vs. S1 and S1.1, respectively), with comparable or better performance on MATH500 and GPQA-Diamond. We further show that P-TTS enhances zero-shot generalization accuracy on out-of-domain reasoning benchmarks of Gaokao, Kaoyan, OlympiadBench, AMC23, GradeSchoolMath, and Minerva. Our analysis suggests that test-time scaling effectively explores the latent space of reasoning patterns, amplifying LLM problem-solving with minimal annotation overhead, and further unlocking the reasoning potential and capabilities of LLMs. Prompting Test-Time Scaling offers a practical, low-cost way to elicit LLM reasoning in resource-constrained or rapidly evolving domains.
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。