Imagen de Portada

The Capabilities and Limitations of Weak-to-Strong Generalization: Generalization and Calibration

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yao, Wei, Yang, Wenkai, Xu, Gengze, Wang, Ziqiao, Lin, Yankai, Liu, Yong
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

On Weak-to-Strong Generalization and f-Divergence
por: Yao, Wei, et al.
Publicado: (2025)

On the Emergence of Weak-to-Strong Generalization: A Bias-Variance Perspective
por: Xu, Gengze, et al.
Publicado: (2025)

Revisiting Weak-to-Strong Generalization in Theory and Practice: Reverse KL vs. Forward KL
por: Yao, Wei, et al.
Publicado: (2025)

On the Blessing of Pre-training in Weak-to-Strong Generalization
por: Yao, Wei, et al.
Publicado: (2026)

Theoretical Insights into Fine-Tuning Attention Mechanism: Generalization and Optimization
por: Yao, Xinhao, et al.
Publicado: (2024)

Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization
por: Yang, Wenkai, et al.
Publicado: (2024)

Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation
por: Yang, Wenkai, et al.
Publicado: (2026)

On the Limitations and Capabilities of Position Embeddings for Length Generalization
por: Chen, Yang, et al.
Publicado: (2025)

Generalization Bounds via Conditional $f$-Information
por: Wang, Ziqiao, et al.
Publicado: (2024)

Theoretical Analysis of Weak-to-Strong Generalization
por: Lang, Hunter, et al.
Publicado: (2024)

Quantifying the Gain in Weak-to-Strong Generalization
por: Charikar, Moses, et al.
Publicado: (2024)

On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization
por: Lin, Yong, et al.
Publicado: (2024)

SteinGen: Generating Fidelitous and Diverse Graph Samples
por: Reinert, Gesine, et al.
Publicado: (2024)

Weak-to-Strong Generalization with Failure Trajectories: A Tree-based Approach to Elicit Optimal Policy in Strong Models
por: Ye, Ruimeng, et al.
Publicado: (2025)

DeepCritic: Deliberate Critique with Large Language Models
por: Yang, Wenkai, et al.
Publicado: (2025)

On the Mechanisms of Weak-to-Strong Generalization: A Theoretical Perspective
por: Moniri, Behrad, et al.
Publicado: (2025)

Provable Weak-to-Strong Generalization via Benign Overfitting
por: Wu, David X., et al.
Publicado: (2024)

Weak-to-Strong Generalization is Nearly Inevitable (in Linear Models)
por: Geng, Scott, et al.
Publicado: (2026)

Weak-to-Strong Generalization under Distribution Shifts
por: Jeon, Myeongho, et al.
Publicado: (2025)

Weak-to-Strong Generalization Even in Random Feature Networks, Provably
por: Medvedev, Marko, et al.
Publicado: (2025)

Two Facets of SDE Under an Information-Theoretic Lens: Generalization of SGD via Training Trajectories and via Terminal States
por: Wang, Ziqiao, et al.
Publicado: (2022)

Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models
por: Pawelczyk, Martin, et al.
Publicado: (2024)

Weak-to-Strong Generalization Through the Data-Centric Lens
por: Shin, Changho, et al.
Publicado: (2024)

Generalization in Federated Learning: A Conditional Mutual Information Framework
por: Wang, Ziqiao, et al.
Publicado: (2025)

The Mechanism of Weak-to-Strong Generalization: Feature Elicitation from Latent Knowledge
por: Awano, Ryoya, et al.
Publicado: (2026)

DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models
por: Yin, Cheng, et al.
Publicado: (2025)

Zero-to-Strong Generalization: Eliciting Strong Capabilities of Large Language Models Iteratively without Gold Labels
por: Liu, Chaoqun, et al.
Publicado: (2024)

Exploring the Generalization Capabilities of AID-based Bi-level Optimization
por: Chen, Congliang, et al.
Publicado: (2024)

From Linear to Nonlinear: Provable Weak-to-Strong Generalization through Feature Learning
por: Oh, Junsoo, et al.
Publicado: (2025)

High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws
por: Ildiz, M. Emrullah, et al.
Publicado: (2024)

LaSeR: Reinforcement Learning with Last-Token Self-Rewarding
por: Yang, Wenkai, et al.
Publicado: (2025)

Bayesian WeakS-to-Strong from Text Classification to Generation
por: Cui, Ziyun, et al.
Publicado: (2024)

Trust Functions: Near-Lossless Weak-to-Strong Generalization by Learning When to Trust the Weak Teacher
por: Uzunoglu, Arda, et al.
Publicado: (2026)

Weak-to-Strong Generalization beyond Accuracy: a Pilot Study in Safety, Toxicity, and Legal Reasoning
por: Ye, Ruimeng, et al.
Publicado: (2024)

Improved Scaling Laws via Weak-to-Strong Generalization in Random Feature Ridge Regression
por: Wu, Diyuan, et al.
Publicado: (2026)

EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles
por: Agrawal, Aakriti, et al.
Publicado: (2024)

Rethinking Training Dynamics in Scale-wise Autoregressive Generation
por: Zhou, Gengze, et al.
Publicado: (2025)

Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions
por: Xue, Yihao, et al.
Publicado: (2025)

Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimension
por: Dong, Yijun, et al.
Publicado: (2025)

Capabilities and Fundamental Limits of Latent Chain-of-Thought
por: Zou, Jiaxuan, et al.
Publicado: (2026)