通过语义相似性动态剪枝，让大模型推理更快更省资源
Chopping Trees: Semantic Similarity Based Dynamic Pruning for Tree-of-Thought Reasoning
- 实时检测并合并语义重复的推理分支，减少冗余计算
- 在GSM8K和MATH500上提速2.3倍，节点数减少85%-90%
- 适合需要高效推理的场景，如在线问答与数学解题
树状思维（ToT）推理能提升大语言模型的问题求解能力，但因语义冗余导致计算开销大，不同分支常探索等价推理路径。我们提出基于语义相似性的动态剪枝（SSDP），据我们所知是首个将在线语义合并集成到并行化树搜索中的轻量级框架，可实现实时聚类与剪枝冗余步骤。在多个推理基准测试中，包括GSM8K和MATH500，SSDP相较当前最优树搜索基线实现最高2.3倍加速，同时保持竞争力的准确率（通常在最强基线的5%以内），并将探索节点数减少85%-90%，展现出一种实用、可扩展的大模型推理优化方案。SSDP的代码已公开于https://github.com/kimjoonghokim/SSDP。
原文摘要 · Abstract (English)
Tree-of-Thought (ToT) reasoning boosts the problem-solving abilities of Large Language Models (LLMs) but is computationally expensive due to semantic redundancy, where distinct branches explore equivalent reasoning paths. We introduce Semantic Similarity-Based Dynamic Pruning (SSDP), a lightweight method that, to the best of our knowledge, is the first framework to integrate online semantic merging into parallelized tree search, enabling the clustering and pruning of redundant steps in real time. Across reasoning benchmarks, including GSM8K and MATH500, SSDP achieves up to a 2.3x speedup over state-of-the-art tree-search baselines while maintaining competitive accuracy (typically within 5% of the strongest baseline) and reducing the number of explored nodes by 85-90%, demonstrating a practical approach to efficient, scalable LLM reasoning. The implementation of SSDP is publicly available at https://github.com/kimjoonghokim/SSDP.
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。