辅助度量帮助解码野生中的技能神经元
Auxiliary Metrics Help Decoding Skill Neurons in the Wild
AI总结：
本文提出一种方法，通过辅助度量解码技能神经元，验证了其在多种任务中的有效性。
摘要：
大型语言模型（LLMs）在广泛的任务中表现出显著的能力，但其内部机制仍 largely opaque。在本文中，我们介绍了一种简单、轻量且广泛适用的方法，重点是隔离编码特定技能的神经元。基于先前工作通过软提示训练在分类任务中识别
英文摘要：
Large language models (LLMs) exhibit remarkable capabilities across a wide range of tasks, yet their internal mechanisms remain largely opaque. In this paper, we introduce a simple, lightweight, and broadly applicable method with a focus on isolating neurons that encode specific skills. Building upon prior work that identified "skill neurons" via soft prompt training on classification tasks, our approach extends the analysis to complex scenarios involving multiple skills. We correlate neuron activations with auxiliary metrics -- such as external labels and the model's own confidence score -- thereby uncovering interpretable and task-specific behaviors without the need for manual token aggregation. We empirically validate our method on tasks spanning open-ended text generation and natural language inference, demonstrating its ability to detect neurons that not only drive known skills but also reveal previously unidentified shortcuts in arithmetic reasoning on BigBench.
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。
