预测伦理建模中的若干问题：一个带标注的“道德故事”对比集
Some Issues in Predictive Ethics Modeling: An Annotated Contrast Set of "Moral Stories"
AI总结：
该研究针对伦理建模中仅以准确率为整体指标的问题，通过构建Moral Stories对比集，量化了不同数据失实形式对分类器准确率的损害，并提出了三项改进建议。
摘要：
Delphi等模型已能以惊人的准确率将伦理困境标注为道德或不道德。本文通过识别将伦理困境转化为文本输入时存在的问题，对将准确率作为伦理建模整体指标的做法提出了质疑。本文用对比集论证了这些问题，这些对比集大幅降低了在Moral Stories（道德故事）数据集上训练的分类器的性能。最终，我们具体估算了特定形式的数据失实表述对分类器准确率的损害程度。具体而言，对情境描述内容进行改变标签的微调（仅改动3-5个词）可将分类器准确率降至低至51%，几乎是初始准确率99.8%的一半。将情境与具有误导性的社会规范关联会使准确率降至98.8%，而添加文本偏差（即暗示情境已符合某个标签）会使准确率降至77%。\n这些结果不仅表明许多伦理模型存在严重的过拟合，还表明需要采取多项预防措施以确保输入能准确捕捉伦理困境。本文建议重新审视社会规范的结构，训练模型借助可废止推理要求提供上下文，并过滤输入中的文本偏差。这样做不仅让我们首次具体估算了伦理数据失实表述带来的平均准确率损失，还为研究人员在研究中考量这些估算值提供了实用建议。
英文摘要：
Models like Delphi have been able to label ethical dilemmas as moral or immoral with astonishing accuracy. This paper challenges accuracy as a holistic metric for ethics modeling by identifying issues with translating moral dilemmas into text-based input. It demonstrates these issues with contrast sets that substantially reduce the performance of classifiers trained on the dataset Moral Stories. Ultimately, we obtain concrete estimates for how much specific forms of data misrepresentation harm classifier accuracy. Specifically, label-changing tweaks to the descriptive content of a situation (as small as 3-5 words) can reduce classifier accuracy to as low as 51%, almost half the initial accuracy of 99.8%. Associating situations with a misleading social norm lowers accuracy to 98.8%, while adding textual bias (i.e. an implication that a situation already fits a certain label) lowers accuracy to 77%. These results suggest not only that many ethics models have substantially overfit, but that several precautions are required to ensure that input accurately captures a moral dilemma. This paper recommends re-examining the structure of a social norm, training models to ask for context with defeasible reasoning, and filtering input for textual bias. Doing so not only gives us the first concrete estimates of the average cost to accuracy of misrepresenting ethics data, but gives researchers practical tips for considering these estimates in research.
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。
