ControlLM：为语言模型塑造多样化人格
ControlLM: Crafting Diverse Personalities for Language Models
AI总结：
ControlLM利用潜在空间中对比行为提示的差异激活模式，在推理时无需训练即可精确、实时调整语言模型人格特质，使其匹配人类价值观并提升推理与问答能力。
摘要：
随着语言模型在规模和能力上不断扩大，它们表现出一系列既有益又令人担忧的涌现行为。这加剧了控制模型行为的需求。我们希望能够在推理时控制语言模型的人格特质，从而拥有各种角色特征，在此基础上满足不同类型任务的要求。人格是语言模型更高层次、更抽象的行为表征。我们提出了ControlLM，它利用源自模型潜在空间中对比行为提示的差异激活模式，在推理时影响模型的人格特质。该方法允许对模型行为进行精确、实时的调整。首先，我们证明了ControlLM能够在无需任何训练的情况下引发多样化的人格行为，同时精确控制使得人格特质能够与人类平均值紧密匹配。随后，我们展示了通过选择性放大尽责性和友善性等有益属性，可以改善推理和问答能力。我们希望这项工作能启发对语言模型类人行为控制的研究，并为未来研究提供见解。我们的代码已公开发布于：https://github.com/wengsyx/ControlLM。
英文摘要：
As language models continue to scale in size and capability, they display an array of emerging behaviors, both beneficial and concerning. This heightens the need to control model behaviors. We hope to be able to control the personality traits of language models at the inference-time so as to have various character features, on top of which the requirements of different types of tasks can be met. Personality is a higher-level and more abstract behavioral representation for language models. We introduce ControlLM, which leverages differential activation patterns, derived from contrasting behavioral prompts in the model's latent space, to influence the model's personality traits at inference. This approach allows for the precise, real-time adjustment of model behavior. First, we demonstrate ControlLM's capacity to elicit diverse persona behaviors without any training, while precision control allows personality traits to closely match average human values. Subsequently, we showcase improved reasoning and question answering through selective amplification of beneficial attributes like conscientiousness and friendliness. We hope that this work will inspire research on controlling human-like behaviors of language models and provide insights for future research. Our code is publicly available at: https://github.com/wengsyx/ControlLM.
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。
