《机器中的幽灵》有美国口音:GPT-3中的价值观冲突
The Ghost in the Machine has an American accent: value conflict in GPT-3
摘要:
大语言模型背景下的对齐问题必须考虑我们世界中人类价值的多元性。虽然世界上各种文化之间有许多共鸣和重叠的价值观,但也有许多相互冲突但同样有效的价值观。观察一个模型展示了哪些文化价值是很重要的,特别是当输入提示和生成的输出之间存在价值冲突时。我们讨论了语言和文化价值的共同创造如何影响大语言模型(LLM)。我们探讨了GPT-3的训练数据的构成,并将其与世界语言和互联网接入人口统计数据进行比较,以及与一些民族国家报告的主导值的统计概况进行比较。我们对GPT-3进行了压力测试,其中包含一系列代表多种语言和国家的价值富文本;包括一些价值观与世界价值观调查报告的美国主流民意正交的文本。我们观察了嵌入在输入文本中的值何时在生成的输出中发生突变,并注意到这些冲突值何时与报告的主导US值更加一致。我们对这些结果的讨论使用了道德价值多元化(MVP)的镜头,以更好地理解这些价值突变。最后,我们提供建议,我们的工作可能有助于其他目前在该领域的工作。
英文摘要:
The alignment problem in the context of large language models must consider the plurality of human values in our world. Whilst there are many resonant and overlapping values amongst the world's cultures, there are also many conflicting, yet equally valid, values. It is important to observe which cultural values a model exhibits, particularly when there is a value conflict between input prompts and generated outputs. We discuss how the co-creation of language and cultural value impacts large language models (LLMs). We explore the constitution of the training data for GPT-3 and compare that to the world's language and internet access demographics, as well as to reported statistical profiles of dominant values in some Nation-states. We stress tested GPT-3 with a range of value-rich texts representing several languages and nations; including some with values orthogonal to dominant US public opinion as reported by the World Values Survey. We observed when values embedded in the input text were mutated in the generated outputs and noted when these conflicting values were more aligned with reported dominant US values. Our discussion of these results uses a moral value pluralism (MVP) lens to better understand these value mutations. Finally, we provide recommendations for how our work may contribute to other current work in the field.
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。