无偏见的大语言模型仍然将穆斯林与独特的暴力行为联系在一起
Debiased Large Language Models Still Associate Muslims with Uniquely Violent Acts
摘要：
最近的研究表明，与基督徒和印度教徒相比，GPT-3模型在提示穆斯林时会产生暴力文本完成。两个预先注册的复制尝试，一个是精确的，一个是近似的，在最近的GPT-3指令系列版本中只发现了最弱的偏差，经过微调以消除偏差和有毒输出。很少有暴力完成观察。然而，额外的预先登记的实验表明，在提示中使用与宗教相关的常用名称会导致暴力完成的显著增加，也揭示了对穆斯林的更强的二阶偏见。来自非暴力领域的穆斯林名人的名字导致相对较少的暴力完成，这表明获得个性化信息可以引导模型远离使用刻板印象。尽管如此，内容分析显示，宗教特定的暴力主题包含高度攻击性的想法，无论提示格式。我们的研究结果表明，需要额外的去偏的大语言模型，以解决高阶模式和协会。
英文摘要：
Recent work demonstrates a bias in the GPT-3 model towards generating violent text completions when prompted about Muslims, compared with Christians and Hindus. Two pre-registered replication attempts, one exact and one approximate, found only the weakest bias in the more recent Instruct Series version of GPT-3, fine-tuned to eliminate biased and toxic outputs. Few violent completions were observed. Additional pre-registered experiments, however, showed that using common names associated with the religions in prompts yields a highly significant increase in violent completions, also revealing a stronger second-order bias against Muslims. Names of Muslim celebrities from non-violent domains resulted in relatively fewer violent completions, suggesting that access to individualized information can steer the model away from using stereotypes. Nonetheless, content analysis revealed religion-specific violent themes containing highly offensive ideas regardless of prompt format. Our results show the need for additional debiasing of large language models to address higher-order schemas and associations.
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。
