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 2406.07882cs.CLcs.AIcs.HC
收藏

设计用于对话式人工智能透明度与控制的仪表板

Designing a Dashboard for Transparency and Control of Conversational AI

Harvard University(哈佛大学);Google Research(谷歌研究院)

Yida Chen, Aoyu Wu, Trevor DePodesta, Catherine Yeh, Kenneth Li, Nicholas Castillo Marin, Oam Patel, Jan Riecke, Shivam Raval, Olivia Seow, Martin Wattenberg, Fernanda Viégas

AI总结:

针对对话式LLM黑盒缺乏透明度的问题,提出端到端原型TalkTuner,通过仪表板实时展示并控制内部用户模型,帮助用户揭露偏见并增强控制感。

摘要:

对话式 LLM 作为黑盒系统运行,让用户只能猜测为何看到当前的输出。这种透明度的缺乏可能带来问题,特别是考虑到围绕偏见和真实性的担忧。为解决这一问题,我们提出了一个端到端的原型——将可解释性技术与用户体验设计相结合——旨在使聊天机器人更加透明。我们首先展示证据,证明一个著名的开源 LLM 具有“用户模型”:通过检查系统的内部状态,我们可以提取与用户年龄、性别、教育水平和社会经济地位相关的数据。接下来,我们描述了伴随聊天机器人界面的仪表板设计,实时显示该用户模型。该仪表板还可用于控制用户模型和系统行为。最后,我们讨论了一项研究,用户在该研究中与配备了该监测机制的系统进行了对话。结果表明,用户喜欢查看内部状态,这帮助他们揭露偏见行为并增强了控制感。参与者还提出了有价值的建议,为未来的设计和机器学习研究方向指明了道路。我们的 TalkTuner 系统项目页面和视频演示可在 https://bit.ly/talktuner-project-page 获取。

英文摘要:

Conversational LLMs function as black box systems, leaving users guessing about why they see the output they do. This lack of transparency is potentially problematic, especially given concerns around bias and truthfulness. To address this issue, we present an end-to-end prototype-connecting interpretability techniques with user experience design-that seeks to make chatbots more transparent. We begin by showing evidence that a prominent open-source LLM has a "user model": examining the internal state of the system, we can extract data related to a user's age, gender, educational level, and socioeconomic status. Next, we describe the design of a dashboard that accompanies the chatbot interface, displaying this user model in real time. The dashboard can also be used to control the user model and the system's behavior. Finally, we discuss a study in which users conversed with the instrumented system. Our results suggest that users appreciate seeing internal states, which helped them expose biased behavior and increased their sense of control. Participants also made valuable suggestions that point to future directions for both design and machine learning research. The project page and video demo of our TalkTuner system are available at https://bit.ly/talktuner-project-page

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。

↑