追随价值的低语：揭示大语言模型中价值导向行为背后的神经机制
Following the Whispers of Values: Unraveling Neural Mechanisms Behind Value-Oriented Behaviors in LLMs
AI总结：
本文提出ValueExploration框架，通过构建C-voice双语基准，在神经元层面定位并停用编码中国社会价值观的神经元，揭示价值影响大语言模型决策的内部机制，并在四个模型上验证有效性。
摘要：
尽管大语言模型（LLMs）表现出令人印象深刻的性能，但它们可能呈现出由编码价值驱动的意外偏见和有害行为，这强调了理解其背后价值机制的紧迫性。然而，当前研究主要通过外部响应评估这些价值，并侧重于人工智能安全，缺乏可解释性，且未能在现实世界情境中评估社会价值。在本文中，我们提出了一种名为ValueExploration的新框架，旨在神经元层面探索大语言模型中国家社会价值的行为驱动机制。作为案例研究，我们聚焦于中国社会价值观，首先构建了C-voice，这是一个大规模双语基准，用于识别和评估大语言模型中的中国社会价值观。通过利用C-voice，我们随后根据激活差异识别并定位负责编码这些价值的神经元。最后，通过停用这些神经元，我们分析模型行为的变化，揭示价值影响大语言模型决策的内部机制。在四个代表性大语言模型上的广泛实验验证了我们框架的有效性。基准和代码将公开可用。
英文摘要：
Despite the impressive performance of large language models (LLMs), they can present unintended biases and harmful behaviors driven by encoded values, emphasizing the urgent need to understand the value mechanisms behind them. However, current research primarily evaluates these values through external responses with a focus on AI safety, lacking interpretability and failing to assess social values in real-world contexts. In this paper, we propose a novel framework called ValueExploration, which aims to explore the behavior-driven mechanisms of National Social Values within LLMs at the neuron level. As a case study, we focus on Chinese Social Values and first construct C-voice, a large-scale bilingual benchmark for identifying and evaluating Chinese Social Values in LLMs. By leveraging C-voice, we then identify and locate the neurons responsible for encoding these values according to activation difference. Finally, by deactivating these neurons, we analyze shifts in model behavior, uncovering the internal mechanism by which values influence LLM decision-making. Extensive experiments on four representative LLMs validate the efficacy of our framework. The benchmark and code will be available.
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。
