LLM在标注时默认采用哪些人口统计特征？
Which Demographics do LLMs Default to During Annotation?
AI总结：
本研究探讨LLM在无人口统计提示时默认模仿的标注者属性，通过对比不同提示词在POPQUORN数据集上的礼貌与冒犯性标注，发现性别、种族和年龄有显著影响。
摘要：
标注者的人口统计特征和文化背景会影响他们在文本标注中分配的标签——例如，一位老年女性可能会觉得阅读发给“兄弟”的消息具有冒犯性，但一位男性青少年可能会觉得这很合适。因此，承认标签差异以避免社会成员被低估是很重要的。在将大型语言模型（LLM）用于数据标注的背景下，这一观察衍生出两个研究方向，即（1）研究LLM的偏见和固有知识，以及（2）通过使用人口统计信息操纵提示词来注入输出多样性。我们结合了这两个研究方向，并提出问题：当没有给出人口统计信息时，LLM会默认采用哪些人口统计特征？为了回答这个问题，我们评估了LLM固有地模仿人类标注者的哪些属性。此外，我们比较了非人口统计条件提示词和安慰剂条件提示词（例如，“你是一个住在5号房子的标注者”）与人口统计条件提示词（例如，“你是一位45岁的男性，是礼貌标注的专家。你如何评价{实例}”）。我们在POPQUORN数据集上研究了礼貌和冒犯性标注的这些问题，该数据集是以受控方式创建的语料库，用于调查基于人口统计的人类标签差异，此前尚未用于基于LLM的分析。我们观察到人口统计提示中与性别、种族和年龄相关的显著影响，这与之前未发现此类效应的研究形成对比。
英文摘要：
Demographics and cultural background of annotators influence the labels they assign in text annotation -- for instance, an elderly woman might find it offensive to read a message addressed to a "bro", but a male teenager might find it appropriate. It is therefore important to acknowledge label variations to not under-represent members of a society. Two research directions developed out of this observation in the context of using large language models (LLM) for data annotations, namely (1) studying biases and inherent knowledge of LLMs and (2) injecting diversity in the output by manipulating the prompt with demographic information. We combine these two strands of research and ask the question to which demographics an LLM resorts to when no demographics is given. To answer this question, we evaluate which attributes of human annotators LLMs inherently mimic. Furthermore, we compare non-demographic conditioned prompts and placebo-conditioned prompts (e.g., "you are an annotator who lives in house number 5") to demographics-conditioned prompts ("You are a 45 year old man and an expert on politeness annotation. How do you rate {instance}"). We study these questions for politeness and offensiveness annotations on the POPQUORN data set, a corpus created in a controlled manner to investigate human label variations based on demographics which has not been used for LLM-based analyses so far. We observe notable influences related to gender, race, and age in demographic prompting, which contrasts with previous studies that found no such effects.
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。
