Azure AI Content Safety Groundedness Detection

From the creator

Groundedness detection detects whether the text responses of large language models are grounded in the source materials provided by the users. Ungroundedness refers to instances where the LLMs produce information that is non-factual or inaccurate from what was present in the source materials. In this demo, we’ll demonstrate the model’s ability to detect grounded and ungrounded output for both a Q&A conversation structure and summarization. Disclosure: This demo contains an AI-generated voice. Chapters: 00:00 - Introduction 00:28 - Q&A task 01:27 - Summarization task Resources: Azure AI Foundry - https://ai.azure.com Learn Module - https://aka.ms/aacs-studio-workshop

Published 2024-06-04 · Watch on YouTube ↗
Availability and playback restrictions are controlled by the original channel.