集体宪法人工智能：使语言模型与公众意见对齐
Collective Constitutional AI: Aligning a Language Model with Public Input
AI总结：
本文提出集体宪法人工智能（CCAI）多阶段流程，将公众意见收集并整合到语言模型训练中，实验表明该模型在九个社会维度上偏见更低，同时保持语言、数学和有用-无害性能，为公众参与语言模型开发提供了可行路径。
摘要：
越来越多的共识认为，语言模型（LM）开发者不应是LM行为的唯一决定者，因此需要一些方法让更广泛的公众能够集体塑造影响他们的LM系统的行为。为满足这一需求，我们提出了集体宪法人工智能（CCAI）：一个多阶段流程，用于收集公众意见并将其整合到LM中——从确定目标人群，到收集原则，再到训练和评估模型。我们通过创建据我们所知第一个使用集体收集的公众意见进行微调的LM，并将其与使用LM开发者既定原则训练的基线模型进行评估比较，证明了该方法在现实世界中的可行性。我们的定量评估显示了该方法的若干优势：与基线模型相比，经过CCAI训练的模型在九个社会维度上表现出更低的偏见，同时在语言、数学和有用-无害评估上保持了相当的性能。对模型的定性比较表明，这些模型因其各自的宪法基础而存在差异，例如，当面对有争议的话题时，经过CCAI训练的模型倾向于生成以积极方式重新表述问题的回应，而不是拒绝回答。这些结果展示了一条有前景且可行的路径，朝着由公众知情地开发语言模型的方向发展。
英文摘要：
There is growing consensus that language model (LM) developers should not be the sole deciders of LM behavior, creating a need for methods that enable the broader public to collectively shape the behavior of LM systems that affect them. To address this need, we present Collective Constitutional AI (CCAI): a multi-stage process for sourcing and integrating public input into LMs-from identifying a target population to sourcing principles to training and evaluating a model. We demonstrate the real-world practicality of this approach by creating what is, to our knowledge, the first LM fine-tuned with collectively sourced public input and evaluating this model against a baseline model trained with established principles from a LM developer. Our quantitative evaluations demonstrate several benefits of our approach: the CCAI-trained model shows lower bias across nine social dimensions compared to the baseline model, while maintaining equivalent performance on language, math, and helpful-harmless evaluations. Qualitative comparisons of the models suggest that the models differ on the basis of their respective constitutions, e.g., when prompted with contentious topics, the CCAI-trained model tends to generate responses that reframe the matter positively instead of a refusal. These results demonstrate a promising, tractable pathway toward publicly informed development of language models.
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。
