STAGE: Controlled Objective Admission for Multi-Preference LLM Alignment
Multi-preference alignment is often framed as scalarization: combine reward dimensions, then optimize. This leaves a temporal decision underspecified: when should each preference dimension enter policy optimization? We propose \methodname, a stability-guided active-set controller for controlled objective admission. \methodname starts from a small active set, retains admitted objectives, and expands when reward-deviation gates indicate low recent deviation or a patience budget is exhausted. A probing phase estimates a hard-to-easy order, and adaptive weighting emphasizes underperforming active
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzyOverlapping authors or contributors · 62%ray-project/ray →
“Shared author/contributor keys: wang”
- FuzzyOverlapping authors or contributors · 62%bytedance/deer-flow →
“Shared author/contributor keys: wang”
- FuzzyOverlapping authors or contributors · 62%Zeyi-Lin/HivisionIDPhotos →
“Shared author/contributor keys: lin”
- FuzzyOverlapping authors or contributors · 62%hiyouga/LlamaFactory →
“Shared author/contributor keys: lin”
- LinkedLinked via arxiv author · 85%Yongqi Tong →
“STAGE: Controlled Objective Admission for Multi-Preference LLM Alignment”
- LinkedLinked via arxiv author · 85%Zhenyu Zhang →
“STAGE: Controlled Objective Admission for Multi-Preference LLM Alignment”
- LinkedLinked via arxiv author · 85%Ruirui Wang →
“STAGE: Controlled Objective Admission for Multi-Preference LLM Alignment”
- LinkedLinked via arxiv author · 85%Kewei Fu →
“STAGE: Controlled Objective Admission for Multi-Preference LLM Alignment”