University of Cambridge > Talks.cam > Language Technology Lab Seminars > SafetyKit: First Aid for Measuring Safety in Open-domain Conversational Systems

  Browse A-Z

Log in

Googledetails Microsoftdetails

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹ️ Information

SafetyKit: First Aid for Measuring Safety in Open-domain Conversational Systems

Download to your calendar using vCal

If you have a question about this talk, please contact Panagiotis Fytas .

The social impact of natural language processing and its applications has received increasing attention. In this position paper, we focus on the problem of safety for end-to-end conversational AI. We survey the problem landscape therein, introducing a taxonomy of three observed phenomena: the Instigator, Yea-Sayer, and Impostor effects. We then empirically assess the extent to which current tools can measure these effects and current systems display them. We release these tools as part of a “first aid kit” (SafetyKit) to quickly assess apparent safety concerns. Our results show that, while current tools are able to provide an estimate of the relative safety of systems in various settings, they still have several shortcomings. We suggest several future directions and discuss ethical considerations.

This talk is part of the Language Technology Lab Seminars series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Seminar Room 3, Institute for Manufacturing, West Cambridge LR5, CUED. https://us02web.zoom.us/j/81492263459 Meeting ID: 814 9226 3459

Other talks

Afternoon Break Animating urbanism: the demotic multiplicities of seeing cities digitally Coming soon Loke CTR Annual Meeting 2026 - Epigenetics of embryogenesis and placentation Tea and Coffee Break External Seminar - Hilde Nelissen TBC
 

© 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity