思维权重推理：探索神经网络权重以增强大语言模型推理能力
Weight-of-Thought Reasoning: Exploring Neural Network Weights for Enhanced LLM Reasoning
AI总结：
针对大语言模型推理依赖 token 级输出、未考虑内部权重动态的问题，提出思维权重推理方法，通过图消息传递等探索权重空间构建推理节点图，在多类推理任务上性能更优且增强可解释性。
摘要：
大语言模型（LLMs）在使用思维链（CoT）等策略提示时展现出卓越的推理能力。然而，这些方法仅关注 token 级输出，未考虑内部权重动态。我们提出思维权重（WoT）推理，这是一种在推理前检查神经网络权重以识别推理路径的新方法。与现有方法不同，WoT 通过基于图的消息传递、多步推理过程和注意力机制探索权重空间。我们的实现构建了推理节点的互联图。在多种推理任务（三段论、数学、代数、组合和几何）上的实验表明，WoT 相较于传统方法性能更优，尤其在复杂问题上。该方法既提升了性能，又增强了推理过程的可解释性，为增强 LLM 推理能力提供了有前景的方向。
英文摘要：
Large language models (LLMs) have demonstrated remarkable reasoning capabilities when prompted with strategies such as Chain-of-Thought (CoT). However, these approaches focus on token-level output without considering internal weight dynamics. We introduce Weight-of-Thought (WoT) reasoning, a novel approach that examines neural network weights before inference to identify reasoning pathways. Unlike existing methods, WoT explores the weight space through graph-based message passing, multi-step reasoning processes, and attention mechanisms. Our implementation creates an interconnected graph of reasoning nodes. Experiments on diverse reasoning tasks (syllogistic, mathematical, algebraic, combinatorial, and geometric) demonstrate that WoT achieves superior performance compared to traditional methods, particularly for complex problems. This approach leads to both improved performance and greater interpretability of the reasoning process, offering a promising direction for enhancing LLM reasoning capabilities.
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。
