2 papers
cs.LG2026
What Is Lost in Post-Training? Default Collapse and the Loss of In-Context Steerability Across Diverse Perspectives
Jessica Dierking, Itai Shapira, Niclas Boehmer
AI models serving a heterogeneous population must act on the principles appropriate to each user and context. While post-training has been shown to narrow the views large language…
cs.GT2026
Single-Winner Voting on Matchings
Niclas Boehmer, Jessica Dierking
We introduce a single-winner perspective on voting on matchings, in which voters have preferences over possible matchings in a graph, and the goal is to select a single collectivel…