BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//hacksw/handcal//NONSGML v1.0//EN
METHOD:PUBLISH
BEGIN:VEVENT
DTSTAMP:20260614T223032Z
DESCRIPTION:Click for Latest Location Information: http://dgiq-edw2025.data
 versity.net/sessionPop.cfm?confid=164&proposalid=16010\nAs business and IT 
 organizations accelerate GenAI's unpredictable, non-deterministic respo
 nses of conversational chatbots, they present challenges for traditional te
 sting. Enter LLM-as-a-Judge strategies, leveraging AI to validate AI. These
  strategies are rapidly emerging, and the options have some significant dif
 ferences. In this discussion, we will explore some of those differences, in
 cluding classes of metrics essential for validation, design patterns that h
 elp make LLM-as-a-Judge successful, and insights on when and where to measu
 re your AI applications. By the end, you'll be equipped with informatio
 n to identify and prioritize your organization's risk assessment needs 
 and to select the best-fit solution for your governance strategy. &nbs
 p;
DTSTART:20250507T120000
SUMMARY:Managing Gen AI Risks: Leveraging AI to Validate AI
DTEND:20250507T124459
LOCATION: See Description
END:VEVENT
END:VCALENDAR