识别用于任务级可控大语言模型的好神经元和坏神经元
Identifying Good and Bad Neurons for Task-Level Controllable LLMs
AI总结：
NeuronLLM通过对比学习识别任务级可控大语言模型中的好神经元和坏神经元，以提升任务表现和理解能力。
摘要：
大型语言模型在多项选择题回答基准测试中展示了显著的能力，但其大规模神经元背后的复杂机制仍然模糊，这对理解和引导LLM构成了重大挑战。尽管最近的研究在识别某些能力的责任神经元方面取得进展，但这些能力特定的方法在需要协调使用多种能力的任务聚焦场景中不可行。此外，这些方法只关注与任务完成呈正相关的支持神经元，而忽略了具有其他作用（如抑制作用）的神经元，并由于LLM中的偶然行为（即通过偶然回答问题而不是真正理解）导致神经元归因偏差。为了解决这些挑战，我们提出了NeuronLLM，一种新的任务级LLM理解框架，该框架采用生物功能拮抗原理进行LLM神经元识别。关键见解是任务表现由具有两种对立作用的神经元共同决定：促进任务完成的好神经元和抑制任务的坏神经元。NeuronLLM通过对比学习好神经元和坏神经元实现对神经元的全面建模，同时利用增强的问题集来减轻LLM中的偶然行为。在不同大小和家族的LLM上的全面实验显示，NeuronLLM在四个NLP任务中优于现有方法，提供了对LLM功能组织的新见解。
英文摘要：
Large Language Models have demonstrated remarkable capabilities on multiple-choice question answering benchmarks, but the complex mechanisms underlying their large-scale neurons remain opaque, posing significant challenges for understanding and steering LLMs. While recent studies made progress on identifying responsible neurons for certain abilities, these ability-specific methods are infeasible for task-focused scenarios requiring coordinated use of multiple abilities. Moreover, these approaches focus only on supportive neurons that correlate positively with task completion, while neglecting neurons with other roles-such as inhibitive roles-and misled neuron attribution due to fortuitous behaviors in LLMs (i.e., correctly answer the questions by chance rather than genuine understanding). To address these challenges, we propose NeuronLLM, a novel task-level LLM understanding framework that adopts the biological principle of functional antagonism for LLM neuron identification. The key insight is that task performance is jointly determined by neurons with two opposing roles: good neurons that facilitate task completion and bad neurons that inhibit it. NeuronLLM achieves a holistic modeling of neurons via contrastive learning of good and bad neurons, while leveraging augmented question sets to mitigate the fortuitous behaviors in LLMs. Comprehensive experiments on LLMs of different sizes and families show the superiority of NeuronLLM over existing methods in four NLP tasks, providing new insights into LLM functional organization.
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。
