迈向大型语言模型命题逻辑推理的机理理解
Towards a Mechanistic Understanding of Propositional Logical Reasoning in Large Language Models
AI总结：
本文通过分析Qwen3在PropLogic-MI数据集上的表现，揭示了大型语言模型在命题逻辑推理中采用的结构化计算机制。
摘要：
理解大型语言模型（LLMs）如何内部进行逻辑推理仍是一个根本性挑战。尽管先前的机理研究侧重于识别任务特定的电路，但它们并未解答LLMs在命题推理中采用何种计算策略的问题。我们通过全面分析Qwen3（8B和14B）在PropLogic-MI数据集上的表现，该数据集涵盖了11种命题逻辑规则类别，跨越单跳和双跳推理。我们并非问“哪些组件是必要的”，而是问“模型如何组织计算？”我们的分析揭示了一种连贯的计算架构，包含四个相互关联的机制：分阶段计算（逐层处理阶段）、信息传输（在边界标记处的信息流聚合）、事实回溯（持久性重新访问源事实）以及专用注意力头（功能不同的头类型）。这些机制在模型规模、规则类型和推理深度上具有泛化能力，提供了机理证据，表明LLMs为逻辑推理采用结构化的计算策略。
英文摘要：
Understanding how Large Language Models (LLMs) perform logical reasoning internally remains a fundamental challenge. While prior mechanistic studies focus on identifying task specific circuits, they leave open the question of what computational strategies LLMs employ for propositional reasoning. We address this gap with a causal mechanistic analysis on PropLogic-MI, a controlled benchmark of 11 propositional rules across one- and two-hop tasks, applied to three model families (Qwen3, Llama-3.1, Mistral). Rather than asking which components are necessary, we ask how the reasoning process is organized, and identify four interlocking mechanisms: Staged Computation, where early, middle, and late layers take on distinct functional roles; Information Transmission, where semantic content aggregates at boundary tokens; Fact Retrospection, where fact tokens stay causally active as binding lookup in middle layers and as sustained access in late layers under hard reasoning loads; and Specialized Attention Heads that structurally implement these patterns. A prompt-order control that places the query before the facts confirms that this organization is model-internal rather than input-layout-induced. These findings show that pretrained LLMs solve propositional reasoning through a structured, layer-organized process that recurs across models, rule categories, and reasoning hops.
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。
