Image de couverture de livre

Theoretical Modeling of Large Language Model Self-Improvement Training Dynamics Through Solver-Verifier Gap

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sun, Yifan, Liang, Yushan, Zhang, Zhen, Liu, Xin, Teng, Jiaye
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Disentangling Feature Structure: A Mathematically Provable Two-Stage Training Dynamics in Transformers
par: Gong, Zixuan, et autres
Publié: (2025)

SVIP: Towards Verifiable Inference of Open-source Large Language Models
par: Sun, Yifan, et autres
Publié: (2024)

Theoretical Analysis of Sparse Optimization with Reparameterization, Weight Decay, and Adaptive Learning Rate
par: Xu, Huangyu, et autres
Publié: (2026)

Information Theoretic Adversarial Training of Large Language Models
par: Zhang, Yiwei, et autres
Publié: (2026)

Harnessing the Power of Large Language Models for Empathetic Response Generation: Empirical Investigations and Improvements
par: Qian, Yushan, et autres
Publié: (2023)

Adaptive Pruning for Large Language Models with Structural Importance Awareness
par: Zheng, Haotian, et autres
Publié: (2024)

What Makes Looped Transformers Perform Better Than Non-Recursive Ones
par: Gong, Zixuan, et autres
Publié: (2025)

On Predictability of Reinforcement Learning Dynamics for Large Language Models
par: Cai, Yuchen, et autres
Publié: (2025)

AdaZeta: Adaptive Zeroth-Order Tensor-Train Adaption for Memory-Efficient Large Language Models Fine-Tuning
par: Yang, Yifan, et autres
Publié: (2024)

Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model
par: Wu, Jiahao, et autres
Publié: (2026)

Vision-Language Model Dialog Games for Self-Improvement
par: Konyushkova, Ksenia, et autres
Publié: (2025)

Self-Improvement in Language Models: The Sharpening Mechanism
par: Huang, Audrey, et autres
Publié: (2024)

Training and Evaluating Language Models with Template-based Data Generation
par: Zhang, Yifan
Publié: (2024)

PolarMem: A Training-Free Polarized Latent Graph Memory for Verifiable Vision-Language Models
par: Chen, Zhisheng, et autres
Publié: (2026)

Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges
par: Lu, Haoran, et autres
Publié: (2025)

MaZO: Masked Zeroth-Order Optimization for Multi-Task Fine-Tuning of Large Language Models
par: Zhang, Zhen, et autres
Publié: (2025)

Scaling and Transferability of Annealing Strategies in Large Language Model Training
par: Wang, Siqi, et autres
Publié: (2025)

Bridging the Semantic Gap for Categorical Data Clustering via Large Language Models
par: Yang, Zihua, et autres
Publié: (2026)

PTQTP: Post-Training Quantization to Trit-Planes for Large Language Models
par: Xiao, He, et autres
Publié: (2025)

Guiding Large Language Models to Generate Computer-Parsable Content
par: Wang, Jiaye
Publié: (2024)

NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement Learning
par: Liu, Wei, et autres
Publié: (2025)

QuZO: Quantized Zeroth-Order Fine-Tuning for Large Language Models
par: Zhou, Jiajun, et autres
Publié: (2025)

Post Training Quantization of Large Language Models with Microscaling Formats
par: Sharify, Sayeh, et autres
Publié: (2024)

Latent Principle Discovery for Language Model Self-Improvement
par: Ramji, Keshav, et autres
Publié: (2025)

PT$^2$-LLM: Post-Training Ternarization for Large Language Models
par: Yan, Xianglong, et autres
Publié: (2025)

On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language Models
par: Wang, Shumin, et autres
Publié: (2026)

TetraJet-v2: Accurate NVFP4 Training for Large Language Models with Oscillation Suppression and Outlier Control
par: Chen, Yuxiang, et autres
Publié: (2025)

Efficient Training of Large-Scale AI Models Through Federated Mixture-of-Experts: A System-Level Approach
par: Chen, Xiaobing, et autres
Publié: (2025)

Self-Training Elicits Concise Reasoning in Large Language Models
par: Munkhbat, Tergel, et autres
Publié: (2025)

Verified Safe Reinforcement Learning for Neural Network Dynamic Models
par: Wu, Junlin, et autres
Publié: (2024)

Provable Training Data Identification for Large Language Models
par: Liu, Zhenlong, et autres
Publié: (2025)

Dynamic Adversarial Reinforcement Learning for Robust Multimodal Large Language Models
par: Bao, Yicheng, et autres
Publié: (2026)

Self-Trained Verification for Training- and Test-Time Self-Improvement
par: Wu, Chen Henry, et autres
Publié: (2026)

Bridging Large Language Models and Graph Structure Learning Models for Robust Representation Learning
par: Su, Guangxin, et autres
Publié: (2024)

A Theoretical Perspective: How to Prevent Model Collapse in Self-consuming Training Loops
par: Fu, Shi, et autres
Publié: (2025)

Test-Time Training on Graphs with Large Language Models (LLMs)
par: Zhang, Jiaxin, et autres
Publié: (2024)

Self-Improvement as Coherence Optimization: A Theoretical Account
par: Qiu, Tianyi, et autres
Publié: (2026)

ProofSketch: Efficient Verified Reasoning for Large Language Models
par: Sheshanarayana, Disha, et autres
Publié: (2025)

LOGIN: A Large Language Model Consulted Graph Neural Network Training Framework
par: Qiao, Yiran, et autres
Publié: (2024)

FormalMATH: Benchmarking Formal Mathematical Reasoning of Large Language Models
par: Yu, Zhouliang, et autres
Publié: (2025)