Cover Image

Improving Value-based Process Verifier via Low-Cost Variance Reduction

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sun, Zetian, Li, Dongfang, Hu, Baotian, Zhang, Min
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Improving Value-based Process Verifier via Structural Prior Injection
by: Sun, Zetian, et al.
Published: (2025)

Is On-Policy Data always the Best Choice for Direct Preference Optimization-based LM Alignment?
by: Sun, Zetian, et al.
Published: (2025)

CMT: A Memory Compression Method for Continual Knowledge Learning of Large Language Models
by: Li, Dongfang, et al.
Published: (2024)

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

In-Context Learning State Vector with Inner and Momentum Optimization
by: Li, Dongfang, et al.
Published: (2024)

Stabilizing Long-term Multi-turn Reinforcement Learning with Gated Rewards
by: Sun, Zetian, et al.
Published: (2025)

Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning
by: Chen, Zhuoen, et al.
Published: (2026)

Temporal Knowledge Question Answering via Abstract Reasoning Induction
by: Chen, Ziyang, et al.
Published: (2023)

LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding
by: Lin, Gang, et al.
Published: (2026)

LycheeCluster: Efficient Long-Context Inference with Structure-Aware Chunking and Hierarchical KV Indexing
by: Li, Dongfang, et al.
Published: (2026)

SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection
by: Liu, Liangxin, et al.
Published: (2024)

WindowsWorld: A Process-Centric Benchmark of Autonomous GUI Agents in Professional Cross-Application Environments
by: Li, Jinchao, et al.
Published: (2026)

Beyond Chunking: Discourse-Aware Hierarchical Retrieval for Long Document Question Answering
by: Chen, Huiyao, et al.
Published: (2025)

Unlabeled Debiasing in Downstream Tasks via Class-wise Low Variance Regularization
by: Masoudian, Shahed, et al.
Published: (2024)

FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG
by: Zhao, Xinping, et al.
Published: (2024)

VideoVista: A Versatile Benchmark for Video Understanding and Reasoning
by: Li, Yunxin, et al.
Published: (2024)

VisionGraph: Leveraging Large Multimodal Models for Graph Theory Problems in Visual Context
by: Li, Yunxin, et al.
Published: (2024)

VCORE: Variance-Controlled Optimization-based Reweighting for Chain-of-Thought Supervision
by: Gong, Xuan, et al.
Published: (2025)

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

Vision Enhancing LLMs: Empowering Multimodal Knowledge Storage and Sharing in LLMs
by: Li, Yunxin, et al.
Published: (2023)

Process Reward Model with Q-Value Rankings
by: Li, Wendi, et al.
Published: (2024)

ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation
by: Zheng, Jingnan, et al.
Published: (2024)

Direct Value Optimization: Improving Chain-of-Thought Reasoning in LLMs with Refined Values
by: Zhang, Hongbo, et al.
Published: (2025)

LLatrieval: LLM-Verified Retrieval for Verifiable Generation
by: Li, Xiaonan, et al.
Published: (2023)

Logic-Regularized Verifier Elicits Reasoning from LLMs
by: Wang, Xinyu, et al.
Published: (2026)

DIVE: Embedding Compression via Self-Limiting Gradient Updates
by: Zhao, Dongfang
Published: (2026)

AQuilt: Weaving Logic and Self-Inspection into Low-Cost, High-Relevance Data Synthesis for Specialist LLMs
by: Ke, Xiaopeng, et al.
Published: (2025)

Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation
by: Hu, Xinshuo, et al.
Published: (2023)

KELPS: A Framework for Verified Multi-Language Autoformalization via Semantic-Syntactic Alignment
by: Zhang, Jiyao, et al.
Published: (2025)

Beyond Outcome Verification: Verifiable Process Reward Models for Structured Reasoning
by: Pronesti, Massimiliano, et al.
Published: (2026)

CompassJudger-2: Towards Generalist Judge Model via Verifiable Rewards
by: Zhang, Taolin, et al.
Published: (2025)

Efficient Shapley Value-based Non-Uniform Pruning of Large Language Models
by: Sun, Chuan, et al.
Published: (2025)

Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models
by: Kim, Kyuyoung, et al.
Published: (2026)

VerifyBench: Benchmarking Reference-based Reward Systems for Large Language Models
by: Yan, Yuchen, et al.
Published: (2025)

CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward
by: Liu, Shudong, et al.
Published: (2025)

Improving Training Efficiency and Reducing Maintenance Costs via Language Specific Model Merging
by: Dmonte, Alphaeus, et al.
Published: (2026)

MedCite: Can Language Models Generate Verifiable Text for Medicine?
by: Wang, Xiao, et al.
Published: (2025)

Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts
by: Li, Yunxin, et al.
Published: (2024)

NCV: A Node-Wise Consistency Verification Approach for Low-Cost Structured Error Localization in LLM Reasoning
by: Zhang, Yulong, et al.
Published: (2025)

Execution-Verified Reinforcement Learning for Optimization Modeling
by: Guan, Runda, et al.
Published: (2026)