arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2311.01007cs.LGcs.AIcs.HC
收藏

通过习得的自然语言规则与入职培训实现高效的人-AI团队

Effective Human-AI Teams via Learned Natural Language Rules and Onboarding

MIT-IBM Watson AI Lab(MIT-IBM沃森人工智能实验室);Massachusetts Institute of Technology(麻省理工学院);IBM Research(IBM研究院)

Hussein Mozannar, Jimin J Lee, Dennis Wei, Prasanna Sattigeri, Subhro Das, David Sontag

AI总结:

本研究针对人类难以判断何时与AI协作的问题,提出基于数据区域的自然语言规则学习方法,通过入职培训教授规则,提升了人-AI团队的任务准确率。

摘要:

人们正依赖AI智能体协助完成各类任务,人类必须清楚何时该依赖智能体、与智能体协作,或是忽略其建议。本研究提出学习基于数据区域、以自然语言描述的规则,用以说明人类应如何与AI协作。我们提出的新型区域发现算法会在嵌入空间的邻域中找到数据的局部区域,这些区域内人类的先前行为需要被修正。随后,我们使用大语言模型通过迭代对比的流程为每个区域生成描述。接着我们通过入职培训阶段将这些规则教授给人类。通过在目标检测和问答任务上开展的用户研究,我们表明该方法能打造准确率更高的人-AI团队。我们还分别对区域发现算法和描述算法进行了评估。

英文摘要:

People are relying on AI agents to assist them with various tasks. The human must know when to rely on the agent, collaborate with the agent, or ignore its suggestions. In this work, we propose to learn rules, grounded in data regions and described in natural language, that illustrate how the human should collaborate with the AI. Our novel region discovery algorithm finds local regions in the data as neighborhoods in an embedding space where prior human behavior should be corrected. Each region is then described using a large language model in an iterative and contrastive procedure. We then teach these rules to the human via an onboarding stage. Through user studies on object detection and question-answering tasks, we show that our method can lead to more accurate human-AI teams. We also evaluate our region discovery and description algorithms separately.

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。

↑