2 papers
cs.LG2026
Online LLM Personalization from Pairwise Preferences Across Users
Romain Puech, Georgy Salakhutdinov, Dimitris Bertsimas
Large language models can answer the same question in different styles, but users' preferred styles are hidden and vary across users and questions. We study inference-time personal…
econ.EM2025
Transferable Utility Matching Beyond Logit: Computation and Estimation with General Heterogeneity
Alfred Galichon, Antoine Jacquet, Georgy Salakhutdinov
We present a general framework for matching with transferable utility (TU) that accommodates arbitrary heterogeneity without relying on the logit structure. The optimal assignment…