让语言模型像树一样并行探索多个思路，提升推理效率。
TSLM: Tree-Structured Language Modeling for Divergent Thinking
- 用特殊标记构建搜索树结构，支持并行生成多条推理路径。
- 在完整搜索树上训练，避免重复计算公共前缀，提升效率。
- 适合需要系统性发散思维的复杂问题求解任务。
语言模型生成推理过程是顺序进行的，难以在搜索中分离无关的探索路径。我们提出树状语言建模（TSLM），使用特殊标记编码分支结构，使模型能在单次生成过程中同时生成并选择性展开多条搜索路径。通过在包含成功与失败尝试的完整搜索树上训练，TSLM学会内化系统性探索能力，无需重复计算共享前缀。相比外部搜索方法需多次独立前向传播，TSLM实现更强性能与更高推理效率。结果表明，在完整树结构轨迹上进行监督学习，为语言模型发展系统性探索能力提供了一种高效的新范式。
原文摘要 · Abstract (English)
Language models generate reasoning sequentially, preventing them from decoupling irrelevant exploration paths during search. We introduce Tree-Structured Language Modeling (TSLM), which uses special tokens to encode branching structure, enabling models to generate and selectively expand multiple search paths within a single generation process. By training on complete search trees including both successful and failed attempts, TSLM learns to internalize systematic exploration without redundant recomputation of shared prefixes. TSLM achieves robust performance and superior inference efficiency by avoiding the multiple independent forward passes required by external search methods. These results suggest a new paradigm of inference-time scaling for robust reasoning, demonstrating that supervised learning on complete tree-structured traces provides an efficient alternative for developing systematic exploration capabilities in language models.
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。