利用基础模型以最小监督检测策略违规
Using Foundation Models to Detect Policy Violations with Minimal Supervision
AI总结：
本研究结合硬提示与软提示微调技术，利用基础模型实现少监督下的高准确率策略违规检测，同时生成合理解释，并总结出可供产品团队快速落地的开发工作流。
摘要：
基础模型，即在大规模文本语料上预训练的大型神经网络，已彻底变革了自然语言处理（NLP）领域。它们可被直接指令驱动（例如(arXiv:2005.14165)）——这被称为硬提示（hard prompting），也可使用极少数据进行微调（例如(arXiv:2104.08691)）——该技术被称为软提示（soft prompting）。我们旨在利用其能力检测策略违规。我们的贡献如下：我们设计了一种将思维链提示适配于策略违规任务的硬提示，该提示可生成策略违规分类结果，以及用于证明分类合理性的抽取式解释。我们将硬提示与软提示微调相结合，构建出一个仅需极少监督即可达到高准确率的分类器，且该分类器同样可生成解释。尽管监督仅作用于分类结果，我们发现修改后的解释仍与（微调后）模型的响应保持一致。研究过程中，我们还发现了基础模型的若干反直觉特性，例如，添加某个特定类别的示例实际上可能会降低该类别的预测占比，此外还有分词对评分的影响等。基于我们的技术成果，我们为产品团队总结出一套简单工作流，用于快速开发有效的策略违规检测器。
英文摘要：
Foundation models, i.e. large neural networks pre-trained on large text corpora, have revolutionized NLP. They can be instructed directly (e.g. (arXiv:2005.14165)) - this is called hard prompting - and they can be tuned using very little data (e.g. (arXiv:2104.08691)) - this technique is called soft prompting. We seek to leverage their capabilities to detect policy violations. Our contributions are: We identify a hard prompt that adapts chain-of-thought prompting to policy violation tasks. This prompt produces policy violation classifications, along with extractive explanations that justify the classification. We compose the hard-prompts with soft prompt tuning to produce a classifier that attains high accuracy with very little supervision; the same classifier also produces explanations. Though the supervision only acts on the classifications, we find that the modified explanations remain consistent with the (tuned) model's response. Along the way, we identify several unintuitive aspects of foundation models. For instance, adding an example from a specific class can actually reduce predictions of that class, and separately, the effects of tokenization on scoring etc. Based on our technical results, we identify a simple workflow for product teams to quickly develop effective policy violation detectors.
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。
