Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Affiliation:
2
0
3
Ignoring human disagreement in AI evaluation could be a major factor fueling the reproducibility crisis in machine learning.
LLMs can't capture the nuances of human disagreement, but DiADEM, a new architecture that explicitly models annotator demographics, achieves strong disagreement tracking by learning which demographic axes matter most.