解决大型语言模型的社会错误归因:一种基于HCXAI的方法
Addressing Social Misattributions of Large Language Models: An HCXAI-based Approach
AI总结:
本文提出扩展Social Transparency框架,通过增加第五个“W问题”澄清大型语言模型设计者与用户赋予的社会归因,以解决敏感领域中的社会错误归因风险,促进技术的伦理负责任开发与使用。
摘要:
以人为本的可解释AI(HCXAI)主张将社会层面整合到AI解释中。HCXAI话语的核心是Social Transparency(ST)框架,旨在使AI系统的社会与组织语境对用户变得可及。在本研究中,我们建议扩展ST框架,以应对大型语言模型(LLMs)中社会错误归因的风险,特别是在心理健康等敏感领域。事实上,LLMs在模拟角色和人格方面能力卓越,这可能导致设计者意图与用户对社会属性的认知之间产生错位,进而有引发情感操纵和危险行为、认知不公以及无根据信任的风险。为解决这些问题,我们提议通过增加第五个“W问题”来增强ST框架,以澄清由其设计者和用户赋予LLMs的特定社会归因。这一补充旨在弥合LLM能力与用户认知之间的差距,促进基于LLM技术的伦理负责任开发与使用。
英文摘要:
Human-centered explainable AI (HCXAI) advocates for the integration of social aspects into AI explanations. Central to the HCXAI discourse is the Social Transparency (ST) framework, which aims to make the socio-organizational context of AI systems accessible to their users. In this work, we suggest extending the ST framework to address the risks of social misattributions in Large Language Models (LLMs), particularly in sensitive areas like mental health. In fact LLMs, which are remarkably capable of simulating roles and personas, may lead to mismatches between designers' intentions and users' perceptions of social attributes, risking to promote emotional manipulation and dangerous behaviors, cases of epistemic injustice, and unwarranted trust. To address these issues, we propose enhancing the ST framework with a fifth 'W-question' to clarify the specific social attributions assigned to LLMs by its designers and users. This addition aims to bridge the gap between LLM capabilities and user perceptions, promoting the ethically responsible development and use of LLM-based technology.
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。