Imagen de Portada

Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xu, Huimin, Mao, Xin, Li, Feng-Lin, Wu, Xiaobao, Chen, Wang, Zhang, Wei, Luu, Anh Tuan
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

SCOPE: Compress Mathematical Reasoning Steps for Efficient Automated Process Annotation
por: Xu, Huimin, et al.
Publicado: (2025)

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs
por: Lai, Xin, et al.
Publicado: (2024)

Don't Forget Your Reward Values: Language Model Alignment via Value-based Calibration
por: Mao, Xin, et al.
Publicado: (2024)

Unsupervised Hallucination Detection by Inspecting Reasoning Processes
por: Srey, Ponhvoan, et al.
Publicado: (2025)

Step-level Value Preference Optimization for Mathematical Reasoning
por: Chen, Guoxin, et al.
Publicado: (2024)

As Simple as Fine-tuning: LLM Alignment via Bidirectional Negative Feedback Loss
por: Mao, Xin, et al.
Publicado: (2024)

SSPO: Self-traced Step-wise Preference Optimization for Process Supervision and Reasoning Compression
por: Xu, Yuyang, et al.
Publicado: (2025)

Step-Controlled DPO: Leveraging Stepwise Error for Enhanced Mathematical Reasoning
por: Lu, Zimu, et al.
Publicado: (2024)

Self-Guided Process Reward Optimization with Redefined Step-wise Advantage for Process Reinforcement Learning
por: Fei, Wu, et al.
Publicado: (2025)

A Survey on Neural Topic Models: Methods, Applications, and Challenges
por: Wu, Xiaobao, et al.
Publicado: (2024)

Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards
por: Yuan, Youliang, et al.
Publicado: (2025)

Towards the TopMost: A Topic Modeling System Toolkit
por: Wu, Xiaobao, et al.
Publicado: (2023)

Understanding and Preventing Entropy Collapse in RLVR with On-Policy Entropy Flow Optimization
por: Xu, Huimin, et al.
Publicado: (2026)

LogicReward: Incentivizing LLM Reasoning via Step-Wise Logical Supervision
por: Xu, Jundong, et al.
Publicado: (2025)

Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning
por: Deng, Yihe, et al.
Publicado: (2025)

Read as You See: Guiding Unimodal LLMs for Low-Resource Explainable Harmful Meme Detection
por: Pan, Fengjun, et al.
Publicado: (2025)

Are LLMs Good Zero-Shot Fallacy Classifiers?
por: Pan, Fengjun, et al.
Publicado: (2024)

Aspect-Based Summarization with Self-Aspect Retrieval Enhanced Generation
por: Feng, Yichao, et al.
Publicado: (2025)

KDMCSE: Knowledge Distillation Multimodal Sentence Embeddings with Adaptive Angular margin Contrastive Learning
por: Nguyen, Cong-Duy, et al.
Publicado: (2024)

GroupDPO: Memory efficient Group-wise Direct Preference Optimization
por: Leng, Jixuan, et al.
Publicado: (2026)

AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization
por: Wu, Junkang, et al.
Publicado: (2024)

AdaDPO: Self-Adaptive Direct Preference Optimization with Balanced Gradient Updates
por: Chen, Shaolong, et al.
Publicado: (2026)

Towards Reliable Truth-Aligned Uncertainty Estimation in Large Language Models
por: Srey, Ponhvoan, et al.
Publicado: (2026)

AKEW: Assessing Knowledge Editing in the Wild
por: Wu, Xiaobao, et al.
Publicado: (2024)

Learning Uncertainty from Sequential Internal Dispersion in Large Language Models
por: Srey, Ponhvoan, et al.
Publicado: (2026)

Step Guided Reasoning: Improving Mathematical Reasoning using Guidance Generation and Step Reasoning
por: Cao, Lang, et al.
Publicado: (2024)

Uncertainty-Aware Step-wise Verification with Generative Reward Models
por: Ye, Zihuiwen, et al.
Publicado: (2025)

Topic Modeling as Multi-Objective Contrastive Optimization
por: Nguyen, Thong, et al.
Publicado: (2024)

Modeling Dynamic Topics in Chain-Free Fashion by Evolution-Tracking Contrastive Learning and Unassociated Word Exclusion
por: Wu, Xiaobao, et al.
Publicado: (2024)

Step-wise Rubric Rewards for LLM Reasoning
por: Xie, Weichu, et al.
Publicado: (2026)

MRAG: A Modular Retrieval Framework for Time-Sensitive Question Answering
por: Siyue, Zhang, et al.
Publicado: (2024)

SOD: Step-wise On-policy Distillation for Small Language Model Agents
por: Zhong, Qiyong, et al.
Publicado: (2026)

Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards
por: Wu, Xiaobao
Publicado: (2025)

Vision-and-Language Pretraining
por: Nguyen, Thong, et al.
Publicado: (2022)

InfoCTM: A Mutual Information Maximization Perspective of Cross-Lingual Topic Modeling
por: Wu, Xiaobao, et al.
Publicado: (2023)

MUR: Momentum Uncertainty guided Reasoning for Large Language Models
por: Yan, Hang, et al.
Publicado: (2025)

Reasoning Paths Optimization: Learning to Reason and Explore From Diverse Paths
por: Chia, Yew Ken, et al.
Publicado: (2024)

ClozeMath: Improving Mathematical Reasoning in Language Models by Learning to Fill Equations
por: Pham, Quang Hieu, et al.
Publicado: (2025)

DPO-Shift: Shifting the Distribution of Direct Preference Optimization
por: Yang, Xiliang, et al.
Publicado: (2025)

FASTopic: Pretrained Transformer is a Fast, Adaptive, Stable, and Transferable Topic Model
por: Wu, Xiaobao, et al.
Publicado: (2024)