Image de couverture de livre

Advantage-Guided Distillation for Preference Alignment in Small Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gao, Shiping, Wan, Fanqi, Guo, Jiajian, Quan, Xiaojun, Wang, Qifan
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

ProactiveEval: A Unified Evaluation Framework for Proactive Dialogue Agents
par: Liu, Tianjian, et autres
Publié: (2025)

Self-Evolution Fine-Tuning for Policy Optimization
par: Chen, Ruijun, et autres
Publié: (2024)

Weighted-Reward Preference Optimization for Implicit Model Fusion
par: Yang, Ziyi, et autres
Publié: (2024)

Unleashing Implicit Rewards: Prefix-Value Learning for Distribution-Level Optimization
par: Gao, Shiping, et autres
Publié: (2026)

FuseRL: Dense Preference Optimization for Heterogeneous Model Fusion
par: Zhong, Longguang, et autres
Publié: (2025)

FuseChat-3.0: Preference Optimization Meets Heterogeneous Model Fusion
par: Yang, Ziyi, et autres
Publié: (2025)

BlockPruner: Fine-grained Pruning for Large Language Models
par: Zhong, Longguang, et autres
Publié: (2024)

Knowledge Fusion of Large Language Models
par: Wan, Fanqi, et autres
Publié: (2024)

ContraSolver: Self-Alignment of Language Models by Resolving Internal Preference Contradictions
par: Zhang, Xu, et autres
Publié: (2024)

FuseChat: Knowledge Fusion of Chat Models
par: Wan, Fanqi, et autres
Publié: (2024)

SPELL: Self-Play Reinforcement Learning for Evolving Long-Context Language Models
par: Yang, Ziyi, et autres
Publié: (2025)

Capturing Nuanced Preferences: Preference-Aligned Distillation for Small Language Models
par: Gu, Yanggan, et autres
Publié: (2025)

Knowledge Fusion of Chat LLMs: A Preliminary Technical Report
par: Wan, Fanqi, et autres
Publié: (2024)

Knowledge Verification to Nip Hallucination in the Bud
par: Wan, Fanqi, et autres
Publié: (2024)

ProFuser: Progressive Fusion of Large Language Models
par: Shi, Tianyuan, et autres
Publié: (2024)

StoicLLM: Preference Optimization for Philosophical Alignment in Small Language Models
par: Khan, Ishmam, et autres
Publié: (2026)

Discriminative Policy Optimization for Token-Level Reward Models
par: Chen, Hongzhan, et autres
Publié: (2025)

Aspect-Guided Multi-Level Perturbation Analysis of Large Language Models in Automated Peer Review
par: Li, Jiatao, et autres
Publié: (2025)

Knowledge Distillation of Black-Box Large Language Models
par: Chen, Hongzhan, et autres
Publié: (2024)

Probabilistic Token Alignment for Large Language Model Fusion
par: Zeng, Runjia, et autres
Publié: (2025)

Re-evaluating Automatic LLM System Ranking for Alignment with Human Preference
par: Gao, Mingqi, et autres
Publié: (2024)

PsyPlay: Personality-Infused Role-Playing Conversational Agents
par: Yang, Tao, et autres
Publié: (2025)

Project Aletheia: Verifier-Guided Distillation of Backtracking for Small Language Models
par: Dixit, Aradhya, et autres
Publié: (2026)

Impact of Preference Noise on the Alignment Performance of Generative Language Models
par: Gao, Yang, et autres
Publié: (2024)

Assistant-Guided Mitigation of Teacher Preference Bias in LLM-as-a-Judge
par: Liu, Zhuo, et autres
Publié: (2025)

Alirector: Alignment-Enhanced Chinese Grammatical Error Corrector
par: Yang, Haihui, et autres
Publié: (2024)

Feature Alignment-Based Knowledge Distillation for Efficient Compression of Large Language Models
par: Wang, Shuo, et autres
Publié: (2024)

Direct Preference Knowledge Distillation for Large Language Models
par: Li, Yixing, et autres
Publié: (2024)

Hit-RAG: Learning to Reason with Long Contexts via Preference Alignment
par: Liu, Junming, et autres
Publié: (2026)

Stabilizing Policy Optimization via Logits Convexity
par: Chen, Hongzhan, et autres
Publié: (2026)

Re-Thinking the Automatic Evaluation of Image-Text Alignment in Text-to-Image Models
par: Zhang, Huixuan, et autres
Publié: (2025)

Evaluating, Understanding, and Improving Constrained Text Generation for Large Language Models
par: Chen, Xiang, et autres
Publié: (2023)

On-the-fly Preference Alignment via Principle-Guided Decoding
par: Zhu, Mingye, et autres
Publié: (2025)

MiniDisc: Minimal Distillation Schedule for Language Model Compression
par: Zhang, Chen, et autres
Publié: (2022)

FlipGuard: Defending Preference Alignment against Update Regression with Constrained Optimization
par: Zhu, Mingye, et autres
Publié: (2024)

SmallPlan: Leverage Small Language Models for Sequential Path Planning with Simulation-Powered, LLM-Guided Distillation
par: Pham, Quang P. M., et autres
Publié: (2025)

Direct Multi-Turn Preference Optimization for Language Agents
par: Shi, Wentao, et autres
Publié: (2024)

InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference Alignment
par: Wang, Jianing, et autres
Publié: (2024)

CFunModel: A "Funny" Language Model Capable of Chinese Humor Generation and Processing
par: Yu, Zhenghan, et autres
Publié: (2025)

PLaD: Preference-based Large Language Model Distillation with Pseudo-Preference Pairs
par: Zhang, Rongzhi, et autres
Publié: (2024)