揭示大模型执行指令的神经机制，找到关键稀疏组件。
Unveiling Instruction-Specific Neurons & Experts: An Analytical Framework for LLM's Instruction-Following Capabilities
- 提出SPARCOM框架，定位模型中特定指令的稀疏神经元与专家。
- 发现这些组件具有功能通用性和唯一性，对指令执行至关重要。
- 适用于研究模型可解释性、安全对齐与高效微调的科研人员。
大型语言模型（LLM）的微调显著提升了其指令遵循能力，但其背后的计算机制仍不清晰。本研究系统分析了微调如何重构模型计算，通过隔离并分析指令特定的稀疏组件——即密集模型中的神经元，以及混合专家（MoE）架构中的神经元和专家。为此，我们构建了涵盖六个不同类别的平衡指令数据集HexaInst，并提出SPARCOM分析框架，包含三项核心贡献：（1）识别这些稀疏组件的方法；（2）评估其功能通用性与独特性；（3）系统比较其变化。实验表明，这些组件具备功能通用性、独特性，并在指令执行中起关键作用。本工作揭示了微调引发的适应性与稀疏计算基底之间的关系，为可信大模型社区提供了更深层的理解。
原文摘要 · Abstract (English)
The finetuning of Large Language Models (LLMs) has significantly advanced their instruction-following capabilities, yet the underlying computational mechanisms driving these improvements remain poorly understood. This study systematically examines how fine-tuning reconfigures LLM computations by isolating and analyzing instruction-specific sparse components, i.e., neurons in dense models and both neurons and experts in Mixture-of-Experts (MoE) architectures. In particular, we introduce HexaInst, a carefully curated and balanced instructional dataset spanning six distinct categories, and propose SPARCOM, a novel analytical framework comprising three key contributions: (1) a method for identifying these sparse components, (2) an evaluation of their functional generality and uniqueness, and (3) a systematic comparison of their alterations. Through experiments, we demonstrate functional generality, uniqueness, and the critical role of these components in instruction execution. By elucidating the relationship between fine-tuning-induced adaptations and sparse computational substrates, this work provides deeper insights into how LLMs internalize instruction-following behavior for the trustworthy LLM community.
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。