JOURNAL ARTICLE
AlignDistil: Token-Level Language Model Alignment as Adaptive Policy Distillation
Keywords:
Security token Computer science Distillation Language model Artificial intelligence Computer network Chemistry
Metrics
0
Cited By
0.00
FWCI (Field Weighted Citation Impact)
0
Refs
0.12
Citation Normalized Percentile
Is in top 1%
Is in top 10%
Topics
Topic Modeling
Physical Sciences → Computer Science → Artificial Intelligence
Natural Language Processing Techniques
Physical Sciences → Computer Science → Artificial Intelligence
Related Documents
JOURNAL ARTICLE
Length-Adaptive Distillation: Customizing Small Language Model for Dynamic Token Pruning
Chang LiuChongyang TaoJianxin LiangJiazhan FengTao ShenQuzhe HuangDongyan Zhao
Year: 2023 Pages: 4452-4463
JOURNAL ARTICLE
Evolutionary Contrastive Distillation for Language Model Alignment
Julian Katz-SamuelsZheng LiHyokun YunPriyanka NigamYi XuV. Petřı́čekBing YinTrishul Chilimbi
Year: 2024 Pages: 5328-5345
JOURNAL ARTICLE
Token-Aware Editing of Internal Activations for Large Language Model Alignment
Tianbo WangYuqing MaKunwei LiaoChayu YangZhange ZhangJiakai WangXianglong Liu
Year: 2025 Pages: 9482-9520
JOURNAL ARTICLE
Expert-level policy style measurement via knowledge distillation with large language model collaboration
Yujie ZhangBiao HuangWeikang YuanZhuoren JiangLiyuan PengShuai ChenJie-Sheng Tan-Soo
Journal: Information Processing & Management Year: 2025 Vol: 62 (4)Pages: 104090-104090
JOURNAL ARTICLE
Alignment-Enhanced Decoding: Defending Jailbreaks via Token-Level Adaptive Refining of Probability Distributions
Quan LiuZhenhong ZhouLongzhu HeYi LiuWei ZhangSen Su
Year: 2024 Pages: 2802-2816