arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2103.14659cs.AIcs.LG
收藏

语言代理的对齐

Alignment of Language Agents

DeepMind

Zachary Kenton, Tom Everitt, Laura Weidinger, Iason Gabriel, Vladimir Mikulik, Geoffrey Irving

摘要:

为了使人工智能对人类有益,人工智能智能体的行为需要与人类想要的东西保持一致。在本文中,我们讨论了一些语言代理的行为问题,所产生的意外误指定的系统设计师。我们强调了一些方式,可能发生的错误,并讨论了一些行为问题,可能会出现错误的规格,包括欺骗性或操纵性的语言,并审查一些方法来避免这些问题。

英文摘要:

For artificial intelligence to be beneficial to humans the behaviour of AI agents needs to be aligned with what humans want. In this paper we discuss some behavioural issues for language agents, arising from accidental misspecification by the system designer. We highlight some ways that misspecification can occur and discuss some behavioural issues that could arise from misspecification, including deceptive or manipulative language, and review some approaches for avoiding these issues.

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。

↑