基于思维空间探索器的大语言模型推理盲点导航
Blind Spot Navigation in Large Language Model Reasoning with Thought Space Explorer
AI总结：
针对大语言模型推理中因依赖已有思维链方向而存在解空间盲点的问题，提出思维空间探索器TSE框架，通过识别关键节点、多链信息融合生成新节点、连接策略扩分支，在数学和问答基准上提升了推理准确率与效果效率权衡。
摘要：
大语言模型通过思维链（Chain-of-Thought）等链式方法展现出了强大的推理能力。近期研究通过生成并行或树状结构、在长短推理模式间切换，或是将推理步骤与任务表现对齐来优化思维结构。然而，这些方法主要依赖于已生成的思维链逻辑方向，忽略了解空间中未被探索的区域。这一现象被定义为盲点，会限制推理过程的多样性和有效性。为此，我们提出了“思维空间探索器”（Thought Space Explorer, TSE），这是一个用于导航和扩展思维结构以克服大语言模型推理盲点的框架。我们的TSE首先识别具有高影响力的关键节点，接着通过整合多条思维链的信息生成新节点，最后通过连接策略扩展新分支。我们在数学和问答基准上开展了一系列实验。与现有基线方法相比，TSE提升了最终答案和中间推理步骤的准确率，同时在实际部署中保持了更优的效果-效率权衡。
英文摘要：
Large language models have shown strong reasoning capabilities through chain-structured methods such as Chain-of-Thought. Recent studies optimize thought structures by generating parallel or tree-like structures, switching between long and short reasoning modes, or aligning reasoning steps with task performance. However, these approaches mainly rely on previously generated logical directions of the chains, which ignore the unexplored regions of the solution space. Such a phenomenon is defined as blind spots, which limit the diversity and effectiveness of the reasoning process. To this end, we propose the ``Thought Space Explorer'' (TSE), a framework for navigating and expanding thought structures to overcome blind spots in LLM reasoning. Our TSE first identifies key nodes with high impact, then generates new nodes by integrating information from multiple chains. Finally, it extends new branches through connection strategies. We conduct a series of experiments on math and QA benchmarks. Compared with existing baseline methods, TSE improves the accuracy of both the final answer and intermediate reasoning steps, while maintaining a better effectiveness-efficiency trade-off for practical deployment.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
