Imagen de Portada

On-the-fly Preference Alignment via Principle-Guided Decoding

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhu, Mingye, Liu, Yi, Zhang, Lei, Guo, Junbo, Mao, Zhendong
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

FlipGuard: Defending Preference Alignment against Update Regression with Constrained Optimization
por: Zhu, Mingye, et al.
Publicado: (2024)

Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models
por: Liu, Yi, et al.
Publicado: (2025)

Enhancing Persona Following at Decoding Time via Dynamic Importance Estimation for Role-Playing Agents
por: Liu, Yuxin, et al.
Publicado: (2026)

LIRE: listwise reward enhancement for preference alignment
por: Zhu, Mingye, et al.
Publicado: (2024)

SparseRM: A Lightweight Preference Modeling with Sparse Autoencoder
por: Liu, Dengcan, et al.
Publicado: (2025)

Leveraging Robust Optimization for LLM Alignment under Distribution Shifts
por: Zhu, Mingye, et al.
Publicado: (2025)

Alignment-Enhanced Decoding:Defending via Token-Level Adaptive Refining of Probability Distributions
por: Liu, Quan, et al.
Publicado: (2024)

Pyramid-Driven Alignment: Pyramid Principle Guided Integration of Large Language Models and Knowledge Graphs
por: Sun, Lei, et al.
Publicado: (2024)

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding
por: Song, Feifan, et al.
Publicado: (2025)

Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts
por: Yin, Yueqin, et al.
Publicado: (2024)

Nudging: Inference-time Alignment of LLMs via Guided Decoding
por: Fei, Yu, et al.
Publicado: (2024)

P-Aligner: Enabling Pre-Alignment of Language Models via Principled Instruction Synthesis
por: Song, Feifan, et al.
Publicado: (2025)

Personalized LLM Decoding via Contrasting Personal Preference
por: Bu, Hyungjune, et al.
Publicado: (2025)

PAD: Personalized Alignment of LLMs at Decoding-Time
por: Chen, Ruizhe, et al.
Publicado: (2024)

Hit-RAG: Learning to Reason with Long Contexts via Preference Alignment
por: Liu, Junming, et al.
Publicado: (2026)

PMMT: Preference Alignment in Multilingual Machine Translation via LLM Distillation
por: Sun, Shuqiao, et al.
Publicado: (2024)

TODO: Enhancing LLM Alignment with Ternary Preferences
por: Guo, Yuxiang, et al.
Publicado: (2024)

Disentangling Preference Representation and Text Generation for Efficient Individual Preference Alignment
por: Zhang, Jianfei, et al.
Publicado: (2024)

TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching
por: Nguyen, Truong, et al.
Publicado: (2026)

LRHP: Learning Representations for Human Preferences via Preference Pairs
por: Wang, Chenglong, et al.
Publicado: (2024)

ICDPO: Effectively Borrowing Alignment Capability of Others via In-context Direct Preference Optimization
por: Song, Feifan, et al.
Publicado: (2024)

Don't Fine-Tune, Decode: Syntax Error-Free Tool Use via Constrained Decoding
por: Zhang, Kexun, et al.
Publicado: (2023)

Preference Alignment Improves Language Model-Based TTS
por: Tian, Jinchuan, et al.
Publicado: (2024)

Inverse Constitutional AI: Compressing Preferences into Principles
por: Findeis, Arduin, et al.
Publicado: (2024)

Boosting Chart-to-Code Generation in MLLM via Dual Preference-Guided Refinement
por: Zhang, Zhihan, et al.
Publicado: (2025)

PA-RAG: RAG Alignment via Multi-Perspective Preference Optimization
por: Wu, Jiayi, et al.
Publicado: (2024)

CARE: Decoding Time Safety Alignment via Rollback and Introspection Intervention
por: Hu, Xiaomeng, et al.
Publicado: (2025)

Multi-Faceted Self-Consistent Preference Alignment for Query Rewriting in Conversational Search
por: Cao, Zhiyu, et al.
Publicado: (2026)

PGPO: Enhancing Agent Reasoning via Pseudocode-style Planning Guided Preference Optimization
por: Cao, Zouying, et al.
Publicado: (2025)

Self-Guided Defense: Adaptive Safety Alignment for Reasoning Models via Synthesized Guidelines
por: Wang, Yuhang, et al.
Publicado: (2025)

Teaching Your Models to Understand Code via Focal Preference Alignment
por: Wu, Jie, et al.
Publicado: (2025)

Word Alignment as Preference for Machine Translation
por: Wu, Qiyu, et al.
Publicado: (2024)

Preference Ranking Optimization for Human Alignment
por: Song, Feifan, et al.
Publicado: (2023)

Automated Creativity Evaluation for Large Language Models: A Reference-Based Approach
por: Li, Ruizhe, et al.
Publicado: (2025)

DeAL: Decoding-time Alignment for Large Language Models
por: Huang, James Y., et al.
Publicado: (2024)

PITA: Preference-Guided Inference-Time Alignment for LLM Post-Training
por: Bobbili, Sarat Chandra, et al.
Publicado: (2025)

Knowledgeable Preference Alignment for LLMs in Domain-specific Question Answering
por: Zhang, Yichi, et al.
Publicado: (2023)

MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization
por: Lyu, Yougang, et al.
Publicado: (2024)

Entropy-Tree: Tree-Based Decoding with Entropy-Guided Exploration
por: Wei, Longxuan, et al.
Publicado: (2026)

Enhancing Multilingual Counterfactual Generation through Alignment-as-Preference Optimization
por: Wang, Yilong, et al.
Publicado: (2026)