Cover Image

A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhou, Zhi, Tan, Yuhao, Li, Zenan, Yao, Yuan, Guo, Lan-Zhe, Li, Yu-Feng, Ma, Xiaoxing
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Bridging Internal Probability and Self-Consistency for Effective and Efficient LLM Reasoning
by: Zhou, Zhi, et al.
Published: (2025)

Neuro-Symbolic Data Generation for Math Reasoning
by: Li, Zenan, et al.
Published: (2024)

Uncertainty Quantification for LLM-based Code Generation
by: Xu, Senrong, et al.
Published: (2026)

Task Abstention for Large Language Models in Code Generation
by: Zhou, Yanke, et al.
Published: (2026)

FormalML: A Benchmark for Evaluating Formal Subgoal Completion in Machine Learning Theory
by: Yang, Xiao-Wen, et al.
Published: (2025)

Vision-Language Model Selection and Reuse for Downstream Adaptation
by: Tan, Hao-Zhe, et al.
Published: (2025)

VCSearch: Bridging the Gap Between Well-Defined and Ill-Defined Problems in Mathematical Reasoning
by: Tian, Shi-Yu, et al.
Published: (2024)

Proving Olympiad Inequalities by Synergizing LLMs and Symbolic Reasoning
by: Li, Zenan, et al.
Published: (2025)

Calibrating Reasoning in Language Models with Internal Consistency
by: Xie, Zhihui, et al.
Published: (2024)

Learning to Disprove: Formal Counterexample Generation with Large Language Models
by: Li, Zenan, et al.
Published: (2026)

Neuro-Symbolic Proof Generation for Scaling Systems Software Verification
by: He, Baoding, et al.
Published: (2026)

Enabling Small Models for Zero-Shot Selection and Reuse through Model Label Learning
by: Zhang, Jia, et al.
Published: (2024)

Fair Conformal Classification via Learning Representation-Based Groups
by: Xu, Senrong, et al.
Published: (2026)

Softened Symbol Grounding for Neuro-symbolic Systems
by: Li, Zenan, et al.
Published: (2024)

Learning with Logical Constraints but without Shortcut Satisfaction
by: Li, Zenan, et al.
Published: (2024)

Self-Consistency of the Internal Reward Models Improves Self-Rewarding Language Models
by: Zhou, Xin, et al.
Published: (2025)

Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning
by: Wang, Xinglin, et al.
Published: (2024)

Neuro-symbolic Learning Yielding Logical Constraints
by: Li, Zenan, et al.
Published: (2024)

Fully Test-time Adaptation for Tabular Data
by: Zhou, Zhi, et al.
Published: (2024)

NeSyGeo: A Neuro-Symbolic Framework for Multimodal Geometric Reasoning Data Generation
by: Wu, Weiming, et al.
Published: (2025)

Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language Models
by: Yang, Xiao-Wen, et al.
Published: (2025)

Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency Training
by: Tan, Cheng, et al.
Published: (2023)

You Only Submit One Image to Find the Most Suitable Generative Model
by: Zhou, Zhi, et al.
Published: (2024)

Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling
by: Wan, Guangya, et al.
Published: (2024)

Series-to-Series Diffusion Bridge Model
by: Yang, Hao, et al.
Published: (2024)

BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning
by: Li, Yuan, et al.
Published: (2026)

CGI: Identifying Conditional Generative Models with Example Images
by: Zhou, Zhi, et al.
Published: (2025)

TabularMath: Understanding Math Reasoning over Tables with Large Language Models
by: Tian, Shi-Yu, et al.
Published: (2025)

LAST: Leveraging Tools as Hints to Enhance Spatial Reasoning for Multimodal Large Language Models
by: Tian, Shi-Yu, et al.
Published: (2026)

NeSy-Route: A Neuro-Symbolic Benchmark for Constrained Route Planning in Remote Sensing
by: Yang, Ming, et al.
Published: (2026)

Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps
by: Zhou, Yanke, et al.
Published: (2026)

Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning
by: Li, Yiwei, et al.
Published: (2024)

On the Learnability of Test-Time Adaptation: A Recovery Complexity Perspective
by: Zhou, Zhi, et al.
Published: (2026)

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning
by: Zhang, Kongcheng, et al.
Published: (2025)

On Information Self-Locking in Reinforcement Learning for Active Reasoning of LLM agents
by: Zou, Deyu, et al.
Published: (2026)

Neuro-Symbolic Artificial Intelligence: Towards Improving the Reasoning Abilities of Large Language Models
by: Yang, Xiao-Wen, et al.
Published: (2025)

ConSol: Sequential Probability Ratio Testing to Find Consistent LLM Reasoning Paths Efficiently
by: Lee, Jaeyeon, et al.
Published: (2025)

Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation
by: Li, Yiwei, et al.
Published: (2025)

Stepwise Self-Consistent Mathematical Reasoning with Large Language Models
by: Zhao, Zilong, et al.
Published: (2024)

CSRP: Chain-of-Thought Reasoning for Chinese Text Correction via Reinforcement Learning with Efficiency-Aware Rewards
by: Tian, Wei, et al.
Published: (2026)