大语言模型中的角色扮演悖论：推理性能的提升与伦理困境
Role-Play Paradox in Large Language Models: Reasoning Performance Gains and Ethical Dilemmas
AI总结：
该研究揭示了大语言模型角色扮演技术的伦理风险，发现自动调优和不同角色均会放大有害与偏见输出的风险，强调在敏感场景部署时需谨慎处理角色模拟与调优过程。
摘要：
大语言模型（LLMs）中的角色扮演通过模拟多样化的认知视角，增强了其生成上下文相关且高质量回复的能力。然而，我们的研究发现了与该技术相关的重大风险。首先，我们证明自动调优（一种根据问题自动选择模型角色的方法）会导致生成有害输出，即使模型被要求采用中立角色。其次，我们研究了不同角色如何影响生成带有偏见或有害内容的可能性。通过在包含刻板印象和有害问题的基准上进行测试，我们发现角色扮演持续放大了偏见输出的风险。我们的结果强调，在敏感或高风险环境中部署LLMs时，需要仔细考虑角色模拟和调优过程。
英文摘要：
Role-play in large language models (LLMs) enhances their ability to generate contextually relevant and high-quality responses by simulating diverse cognitive perspectives. However, our study identifies significant risks associated with this technique. First, we demonstrate that autotuning, a method used to auto-select models' roles based on the question, can lead to the generation of harmful outputs, even when the model is tasked with adopting neutral roles. Second, we investigate how different roles affect the likelihood of generating biased or harmful content. Through testing on benchmarks containing stereotypical and harmful questions, we find that role-play consistently amplifies the risk of biased outputs. Our results underscore the need for careful consideration of both role simulation and tuning processes when deploying LLMs in sensitive or high-stakes contexts.
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。
