Copertina

SPPD: Self-training with Process Preference Learning Using Dynamic Value Margin

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yi, Hao, Li, Qingyang, Hu, Yulan, Zhang, Fuzheng, Zhang, Di, Liu, Yong
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

TSO: Self-Training with Scaled Preference Optimization
di: Chen, Kaihui, et al.
Pubblicazione: (2024)

Towards Comprehensive Preference Data Collection for Reward Modeling
di: Hu, Yulan, et al.
Pubblicazione: (2024)

Towards Reward Fairness in RLHF: From a Resource Allocation Perspective
di: Ouyang, Sheng, et al.
Pubblicazione: (2025)

Video-Text Dataset Construction from Multi-AI Feedback: Promoting Weak-to-Strong Preference Learning for Video Large Language Models
di: Yi, Hao, et al.
Pubblicazione: (2024)

Graph Ranking Contrastive Learning: A Extremely Simple yet Efficient Method
di: Hu, Yulan, et al.
Pubblicazione: (2023)

Learn More with Less: Uncertainty Consistency Guided Query Selection for RLVR
di: Yi, Hao, et al.
Pubblicazione: (2026)

VIGraph: Generative Self-supervised Learning for Class-Imbalanced Node Classification
di: Hu, Yulan, et al.
Pubblicazione: (2023)

Just Ask One More Time! Self-Agreement Improves Reasoning of Language Models in (Almost) All Scenarios
di: Lin, Lei, et al.
Pubblicazione: (2023)

Coarse-to-Fine Process Reward Modeling for Mathematical Reasoning
di: Hu, Yulan, et al.
Pubblicazione: (2025)

Small-Margin Preferences Still Matter-If You Train Them Right
di: Pang, Jinlong, et al.
Pubblicazione: (2026)

ERABAL: Enhancing Role-Playing Agents through Boundary-Aware Learning
di: Tang, Yihong, et al.
Pubblicazione: (2024)

Refining Latent Representations: A Generative SSL Approach for Heterogeneous Graph Learning
di: Hu, Yulan, et al.
Pubblicazione: (2023)

Learning Top-k Subtask Planning Tree based on Discriminative Representation Pre-training for Decision Making
di: Ruan, Jingqing, et al.
Pubblicazione: (2023)

Beyond Itinerary Planning-A Real-World Benchmark for Multi-Turn and Tool-Using Travel Tasks
di: Cheng, Xiang, et al.
Pubblicazione: (2025)

Inductive-Deductive Strategy Reuse for Multi-Turn Instructional Dialogues
di: Ou, Jiao, et al.
Pubblicazione: (2024)

Routing to the Right Expertise: A Trustworthy Judge for Instruction-based Image Editing
di: Sun, Chenxi, et al.
Pubblicazione: (2025)

Chain-of-Specificity: An Iteratively Refining Method for Eliciting Knowledge from Large Language Models
di: Wei, Kaiwen, et al.
Pubblicazione: (2024)

No More Stale Feedback: Co-Evolving Critics for Open-World Agent Learning
di: Li, Zhicong, et al.
Pubblicazione: (2026)

DMQR-RAG: Diverse Multi-Query Rewriting for RAG
di: Li, Zhicong, et al.
Pubblicazione: (2024)

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

When Modalities Conflict: How Unimodal Reasoning Uncertainty Governs Preference Dynamics in MLLMs
di: Zhang, Zhuoran, et al.
Pubblicazione: (2025)

DialogBench: Evaluating LLMs as Human-like Dialogue Systems
di: Ou, Jiao, et al.
Pubblicazione: (2023)

SynPO: Synergizing Descriptiveness and Preference Optimization for Video Detailed Captioning
di: Dang, Jisheng, et al.
Pubblicazione: (2025)

Leanabell-Prover: Posttraining Scaling in Formal Reasoning
di: Zhang, Jingyuan, et al.
Pubblicazione: (2025)

Legend: Leveraging Representation Engineering to Annotate Safety Margin for Preference Datasets
di: Feng, Duanyu, et al.
Pubblicazione: (2024)

Improving Attributed Text Generation of Large Language Models via Preference Learning
di: Li, Dongfang, et al.
Pubblicazione: (2024)

Beyond Meta-Reasoning: Metacognitive Consolidation for Self-Improving LLM Reasoning
di: Zhuang, Ziqing, et al.
Pubblicazione: (2026)

Self-supervised Preference Optimization: Enhance Your Language Model with Preference Degree Awareness
di: Li, Jian, et al.
Pubblicazione: (2024)

VidCapBench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video Generation
di: Chen, Xinlong, et al.
Pubblicazione: (2025)

COPR: Continual Human Preference Learning via Optimal Policy Regularization
di: Zhang, Han, et al.
Pubblicazione: (2024)

Adaptive Margin RLHF via Preference over Preferences
di: Chittepu, Yaswanth, et al.
Pubblicazione: (2025)

Improving Value-based Process Verifier via Low-Cost Variance Reduction
di: Sun, Zetian, et al.
Pubblicazione: (2025)

OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration
di: Yang, Yiqin, et al.
Pubblicazione: (2026)

GUNDAM: Aligning Large Language Models with Graph Understanding
di: Ouyang, Sheng, et al.
Pubblicazione: (2024)

Subtle Errors in Reasoning: Preference Learning via Error-injected Self-editing
di: Xu, Kaishuai, et al.
Pubblicazione: (2024)

Unitary Multi-Margin BERT for Robust Natural Language Processing
di: Chang, Hao-Yuan, et al.
Pubblicazione: (2024)

Klear-CodeTest: Scalable Test Case Generation for Code Reinforcement Learning
di: Fu, Jia, et al.
Pubblicazione: (2025)

Strong Preferences Affect the Robustness of Preference Models and Value Alignment
di: Xu, Ziwei, et al.
Pubblicazione: (2024)

DSTC: Direct Preference Learning with Only Self-Generated Tests and Code to Improve Code LMs
di: Liu, Zhihan, et al.
Pubblicazione: (2024)

Learning What Matters Now: Dynamic Preference Inference under Contextual Shifts
di: Cao, Xianwei, et al.
Pubblicazione: (2026)