发现大模型内部存在支持抽象推理的符号机制。
Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models
- 通过三步计算实现符号化推理：抽象、归纳、检索。
- 早期层将输入转为抽象变量，中间层进行序列归纳。
- 适合关注模型内在推理机制的研究者阅读。
近期多项研究发现大语言模型（LLMs）具备涌现式推理能力，但其稳健性及是否依赖结构化推理机制仍存争议。为此，我们研究了LLMs中支持抽象推理的内部机制。发现了一种涌现的符号架构，通过三个阶段的计算实现抽象推理：在早期层，符号抽象头基于输入标记间的关联将标记转换为抽象变量；在中间层，符号归纳头对这些抽象变量执行序列归纳；在后期层，检索头通过查找与预测抽象变量相关联的值来预测下一个标记。这些结果为符号与神经网络方法之间的长期争论提供了新视角，表明神经网络中的涌现推理依赖于符号机制的出现。
原文摘要 · Abstract (English)
Many recent studies have found evidence for emergent reasoning capabilities in large language models (LLMs), but debate persists concerning the robustness of these capabilities, and the extent to which they depend on structured reasoning mechanisms. To shed light on these issues, we study the internal mechanisms that support abstract reasoning in LLMs. We identify an emergent symbolic architecture that implements abstract reasoning via a series of three computations. In early layers, symbol abstraction heads convert input tokens to abstract variables based on the relations between those tokens. In intermediate layers, symbolic induction heads perform sequence induction over these abstract variables. Finally, in later layers, retrieval heads predict the next token by retrieving the value associated with the predicted abstract variable. These results point toward a resolution of the longstanding debate between symbolic and neural network approaches, suggesting that emergent reasoning in neural networks depends on the emergence of symbolic mechanisms.
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。