Pref-CTRL trains a multi-objective value function on preferences to guide representation editing for LLM alignment, outperforming RE-Control on benchmarks with better out-of-domain generalization.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CL 3years
2026 3representative citing papers
Align-Cultura introduces the CULTURAX dataset and shows that culturally fine-tuned LLMs improve joint HHH scores by 4-6%, cut cultural failures by 18%, and gain 10-12% efficiency with minimal leakage.
citing papers explorer
-
Pref-CTRL: Preference Driven LLM Alignment using Representation Editing
Pref-CTRL trains a multi-objective value function on preferences to guide representation editing for LLM alignment, outperforming RE-Control on benchmarks with better out-of-domain generalization.
-
AlignCultura: Towards Culturally Aligned Large Language Models?
Align-Cultura introduces the CULTURAX dataset and shows that culturally fine-tuned LLMs improve joint HHH scores by 4-6%, cut cultural failures by 18%, and gain 10-12% efficiency with minimal leakage.
- From Concept-Aligned Tokens to Vulnerable Features: Mechanistic Localization of Jailbreaks