Image de couverture de livre

Hard Negative Sample-Augmented DPO Post-Training for Small Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Lu, Haocheng, Zhu, Minjun, Yu, Henry
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Supervised Contrastive Learning with Hard Negative Samples
par: Jiang, Ruijie, et autres
Publié: (2022)

Random Is Hard to Beat: Active Selection in online DPO with Modern LLMs
par: Oh, Giyeong, et autres
Publié: (2026)

Momentum Contrastive Learning with Enhanced Negative Sampling and Hard Negative Filtering
par: Hoang, Duy, et autres
Publié: (2025)

When Hard Negatives Hurt: Bridging the Generative-Discriminative Gap in Hard Negative Synthesis for Retrieval
par: Zhang, Zhicheng, et autres
Publié: (2026)

Reveal the Mystery of DPO: The Connection between DPO and RL Algorithms
par: Su, Xuerui, et autres
Publié: (2025)

Post-Training Augmentation Invariance
par: Eikenberry, Keenan, et autres
Publié: (2025)

MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimization
par: Surana, Rohan, et autres
Publié: (2026)

Bootstrapping Language Models with DPO Implicit Rewards
par: Chen, Changyu, et autres
Publié: (2024)

Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment
par: Xiao, Teng, et autres
Publié: (2024)

DiaTool-DPO: Multi-Turn Direct Preference Optimization for Tool-Augmented Large Language Models
par: Jung, Sunghee, et autres
Publié: (2025)

g-DPO: Scalable Preference Optimization for Protein Language Models
par: Ferragu, Constance, et autres
Publié: (2025)

Gradient-Gated DPO: Stabilizing Preference Optimization in Language Models
par: Mouiche, Inoussa
Publié: (2026)

A Post-Training Enhanced Optimization Approach for Small Language Models
par: Zhai, Keke
Publié: (2024)

Exploring Layer-wise Information Effectiveness for Post-Training Quantization in Small Language Models
par: Xiao, He, et autres
Publié: (2025)

Boosting Protein Language Models with Negative Sample Mining
par: Xu, Yaoyao, et autres
Publié: (2024)

Layer-diverse Negative Sampling for Graph Neural Networks
par: Duan, Wei, et autres
Publié: (2024)

Saten: Sparse Augmented Tensor Networks for Post-Training Compression of Large Language Models
par: Solgi, Ryan, et autres
Publié: (2025)

Hard-Negative Sampling for Contrastive Learning: Optimal Representation Geometry and Neural- vs Dimensional-Collapse
par: Jiang, Ruijie, et autres
Publié: (2023)

Contrastive Learning with Negative Sampling Correction
par: Wang, Lu, et autres
Publié: (2024)

Robust Training of Temporal GNNs using Nearest Neighbours based Hard Negatives
par: Gupta, Shubham, et autres
Publié: (2024)

Provably Robust DPO: Aligning Language Models with Noisy Feedback
par: Chowdhury, Sayak Ray, et autres
Publié: (2024)

SCONE: A Novel Stochastic Sampling to Generate Contrastive Views and Hard Negative Samples for Recommendation
par: Lee, Chaejeong, et autres
Publié: (2024)

Learning Dynamics in RL Post-Training for Language Models
par: Tomihari, Akiyoshi
Publié: (2026)

On the Plasticity and Stability for Post-Training Large Language Models
par: Qiang, Wenwen, et autres
Publié: (2026)

Synthetic Data Generation for Augmenting Small Samples
par: Liu, Dan, et autres
Publié: (2025)

What Matters in Data for DPO?
par: Pan, Yu, et autres
Publié: (2025)

Investigating the Impact of Hard Samples on Accuracy Reveals In-class Data Imbalance
par: Pukowski, Pawel, et autres
Publié: (2024)

ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment
par: Lin, Xiaoqiang, et autres
Publié: (2025)

SFBD Flow: A Continuous-Optimization Framework for Training Diffusion Models with Noisy Samples
par: Lu, Haoye, et autres
Publié: (2025)

Take the Bull by the Horns: Hard Sample-Reweighted Continual Training Improves LLM Generalization
par: Chen, Xuxi, et autres
Publié: (2024)

HBVLA: Pushing 1-Bit Post-Training Quantization for Vision-Language-Action Models
par: Yan, Xin, et autres
Publié: (2026)

Evaluating Synthetic Tabular Data Generated To Augment Small Sample Datasets
par: Marin, Javier
Publié: (2022)

Computational Bottlenecks of Training Small-scale Large Language Models
par: Ashkboos, Saleh, et autres
Publié: (2024)

Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search
par: Gu, Yuxian, et autres
Publié: (2025)

Efficient Post-Training Pruning of Large Language Models with Statistical Correction
par: Yu, Peiqi, et autres
Publié: (2026)

DiRL: An Efficient Post-Training Framework for Diffusion Language Models
par: Zhu, Ying, et autres
Publié: (2025)

TADA: Improved Diffusion Sampling with Training-free Augmented Dynamics
par: Chen, Tianrong, et autres
Publié: (2025)

Better World Models Can Lead to Better Post-Training Performance
par: Gupta, Prakhar, et autres
Publié: (2025)

A Unified View of Delta Parameter Editing in Post-Trained Large-Scale Models
par: Tang, Qiaoyu, et autres
Publié: (2024)

Group Causal Policy Optimization for Post-Training Large Language Models
par: Gu, Ziyin, et autres
Publié: (2025)