Guangyu Du

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Constitutional AI & AI Ethics (1)RLHF & Preference Learning (1)

Frequent co-authors

L. H. Nguyen (1)Long Hoang Nguyen (1)Brice Valentin Kok-Shun (1)Ali Sunyaev (1)

Papers (1)

Aug 13, 2026

L. H. Nguyen +42w ago·also TU Munich

Follow the Norm: Accounting for Fine-Tuning and Prompt Effects on Model Rationales

Norm-breaking fine-tuning can shift AI rationales from safety compliance to self-interest, raising critical questions about model alignment and oversight.

L. H. Nguyen, Long Hoang Nguyen, Brice Valentin Kok-Shun +2

Constitutional AI & AI Ethics RLHF & Preference Learning

Search

Guangyu Du

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)