立场论文:迈向双向的人类-AI对齐
Position: Towards Bidirectional Human-AI Alignment
AI总结:
本文综述400余篇论文,提出双向人类-AI对齐框架,强调AI适配人类价值与人类认知、行为及社会适应AI并重,并指出研究空白与未来挑战。
摘要:
通用人工智能的最新进展凸显出使AI系统与人类目标和价值观保持一致的迫切需求。然而,对于何为“对齐”缺乏清晰、共同的理解,限制了有意义的进展和跨学科协作。在这篇立场论文中,我们主张研究界应明确定义并批判性反思“对齐”,以解释人类与AI之间双向且动态的关系。通过系统回顾涵盖HCI、NLP、ML等领域的400多篇论文,我们考察了当前对齐是如何被定义和操作化的。在该分析基础上,我们提出Bidirectional Human-AI Alignment(双向人类-AI对齐)框架,它不仅纳入了使AI与人类价值观对齐的传统努力,还引入了使人类与AI对齐这一关键且未被充分探索的维度——支持在认知、行为和社会层面对快速发展的AI技术进行适应。我们的发现揭示了当前文献中的显著空白,尤其是在长期交互设计、人类价值建模和相互理解方面。我们最后提出三项核心挑战和可行动建议,以引导未来研究走向更细致、互惠的人类-AI对齐方法。
英文摘要:
Recent advances in general-purpose AI underscore the urgent need to align AI systems with human goals and values. Yet, the lack of a clear, shared understanding of what constitutes "alignment" limits meaningful progress and cross-disciplinary collaboration. In this position paper, we argue that the research community should explicitly define and critically reflect on "alignment" to account for the bidirectional and dynamic relationship between humans and AI. Through a systematic review of over 400 papers spanning HCI, NLP, ML, and more, we examine how alignment is currently defined and operationalized. Building on this analysis, we introduce the Bidirectional Human-AI Alignment framework, which not only incorporates traditional efforts to align AI with human values but also introduces the critical, underexplored dimension of aligning humans with AI -- supporting cognitive, behavioral, and societal adaptation to rapidly advancing AI technologies. Our findings reveal significant gaps in current literature, especially in long-term interaction design, human value modeling, and mutual understanding. We conclude with three central challenges and actionable recommendations to guide future research toward more nuanced, reciprocal, and human-AI alignment approaches.
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。