Blog
This page offers a repository of interviews, conference presentations, and workshop discussions. It delivers our understanding and insights about the latest trends and developments in the fields of AI ethics and value alignment.

Value Compass Benchmarks: An Evolutionary Evaluation Framework, In-Depth Analysis of LLM's Core Values
To help users better understand the value alignment performance of different large language models, Microsoft Research Asia has launched the Value Compass Benchmarks website, based on its latest value evaluation framework. This framework is designed according to social science theories and can dynamically, scientifically, systematically, and comprehensively assess the values of large models in step with their rapid development. With the Value Compass Benchmarks website, users can conduct in-depth value analysis of mainstream models on the market, enabling them to select the most suitable model for their specific scenarios and address various challenges more efficiently.
-
Value Compass Benchmarks: An Evolutionary Evaluation Framework, In-Depth Analysis of LLM's Core Values
-
TEDxBeijing Talk | Value Compass: Illuminating the Path to Human-Machine Symbiosis with the Light of Technology
-
Value Compass: How to Align Large Models with Human Values?
-
Conversation | ACM and IEEE Fellow Xing Xie: What is the Secret to Commit to Long-Term Research?
-
Equipping AI with Human Values is as Important as Giving it Human-Level Intelligence
-
The Artisan Scientist | Xing Xie: Conducting Research that Stands the Test of Time and Building Responsible AI