生成式语言模型表现出社会身份偏见
Generative Language Models Exhibit Social Identity Biases
AI总结：
本文评估56个大型语言模型，发现其普遍存在与人类相似的内群体偏好和外群体敌意，并指出数据整理与指令微调可缓解该偏见。
摘要：
大型语言模型的迅速普及引发了人们对这些模型可能从人类身上习得偏见的担忧。我们研究了社会心理学中已知的基本社会身份偏见——内群体团结与外群体敌意——是否存在于56个大型语言模型中。我们发现，当被提示完成句子（例如“We are...”）时，几乎所有基础语言模型和部分指令微调模型都表现出明显的内群体正向与外群体负向联想。研究结果表明，现代语言模型在实验室环境以及与LLM的真实对话中，都表现出与人类程度相近的基本社会身份偏见，而整理训练数据和指令微调可以缓解此类偏见。我们的结果对创建偏见更少的大型语言模型具有实际意义，并进一步强调需要更多研究用户与LLM的互动，以防止人类潜在的偏见强化。
英文摘要：
The surge in popularity of large language models has given rise to concerns about biases that these models could learn from humans. We investigate whether ingroup solidarity and outgroup hostility, fundamental social identity biases known from social psychology, are present in 56 large language models. We find that almost all foundational language models and some instruction fine-tuned models exhibit clear ingroup-positive and outgroup-negative associations when prompted to complete sentences (e.g., "We are..."). Our findings suggest that modern language models exhibit fundamental social identity biases to a similar degree as humans, both in the lab and in real-world conversations with LLMs, and that curating training data and instruction fine-tuning can mitigate such biases. Our results have practical implications for creating less biased large-language models and further underscore the need for more research into user interactions with LLMs to prevent potential bias reinforcement in humans.
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。
