2 papers
cs.CL2026
Where does output diversity collapse in post-training?
Constantinos Karouzos, Xingwei Tan, Nikolaos Aletras
Post-trained language models produce less varied outputs than their base counterparts. This output diversity collapse undermines inference-time scaling methods that rely on varied…
cs.CL2026
An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift
Constantinos Karouzos, Xingwei Tan, Nikolaos Aletras
Preference tuning aligns base language models to human judgments of quality, helpfulness, or safety by optimizing over explicit preference signals rather than likelihood alone. Pri…