Can we trust AI to judge? Two research teams explore the opportunities and limitations of LLM-as-a-Judge

USE THIS IMAGE FOR MAIN PAGE TILE (centered). Tech Ethics Lab Blog, a collaboration between IBM and the University of Notre Dame.

Laura Moran Walton
Tech Ethics Lab Blog, 2025

View reference article

This post digs into the opportunities and limitations of using LLMs as "digital judges." Researchers funded by the Tech Ethics Lab are developing a practical and nuanced view of how we might make AI judges more transparent, accountable, and value-aligned.