[Adapt] [Seminar] Ethical Issues in Dialogue Systems (II)

[贾琪]

Hi Adapters,
Dialogue systems suffer from different kinds of ethical issues in real applications. Last semester, I talked about some representative ethical issues and a social bias detection framework. Tomorrow, I'll continue this topic and introduce some unsafe phenomena in the aspect of chatbot behaviors, including the origin of these ethical issues, representative unsafe behaviors and current solutions.

The papers covered in my slides are listed as follows:
1. Dinan, Emily, et al. Safetykit: First aid for measuring safety in open-domain conversational systems. ACL’ 2022.
2. Ung, Megan, Jing Xu, and Y-Lan Boureau. SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failures. ACL’ 2022.
3. Xu, Jing, et al. Bot-adversarial dialogue for safe conversational agents. NAACL’ 2021.


Hope you find this talk interesting!

For our online group seminar tomorrow, the Tencent meeting room is as follows:
###############################################################
会议主题：ADAPT Seminar
会议时间：2022/09/21 16:00-18:00 (GMT+08:00) 中国标准时间 - 北京

点击链接入会，或添加至会议列表：
https://meeting.tencent.com/dm/nZ7m05rgBk9P

#腾讯会议：729-937-807

复制该信息，打开手机腾讯会议即可参与
##############################################################

Time: Wed 4:00pm
Venue: Tencent meeting 729-937-807

Best wishes,
Qi Jia
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://cs.sjtu.edu.cn/pipermail/adapt/attachments/20220920/53152179/attachment.htm>