Image de couverture de livre

Theoretical Analysis of Weak-to-Strong Generalization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Lang, Hunter, Sontag, David, Vijayaraghavan, Aravindan
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Learning to Decode Collaboratively with Multiple Language Models
par: Shen, Shannon Zejiang, et autres
Publié: (2024)

Low-Degree Method Fails to Predict Robust Subspace Recovery
par: Jia, He, et autres
Publié: (2026)

Trust Functions: Near-Lossless Weak-to-Strong Generalization by Learning When to Trust the Weak Teacher
par: Uzunoglu, Arda, et autres
Publié: (2026)

Agnostic Learning of Arbitrary ReLU Activation under Gaussian Marginals
par: Guo, Anxin, et autres
Publié: (2024)

Bayesian WeakS-to-Strong from Text Classification to Generation
par: Cui, Ziyun, et autres
Publié: (2024)

EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles
par: Agrawal, Aakriti, et autres
Publié: (2025)

Weak-to-Strong Generalization beyond Accuracy: a Pilot Study in Safety, Toxicity, and Legal Reasoning
par: Ye, Ruimeng, et autres
Publié: (2024)

Agnostic Learning of General ReLU Activation Using Gradient Descent
par: Awasthi, Pranjal, et autres
Publié: (2022)

Fragile Thoughts: How Large Language Models Handle Chain-of-Thought Perturbations
par: Aravindan, Ashwath Vaithinathan, et autres
Publié: (2026)

On the Duality between Gradient Transformations and Adapters
par: Torroba-Hennigen, Lucas, et autres
Publié: (2025)

Towards Verifiable Text Generation with Symbolic References
par: Hennigen, Lucas Torroba, et autres
Publié: (2023)

Weak-to-Strong Elicitation via Mismatched Wrong Drafts
par: Deng, Wei
Publié: (2026)

When In-Distribution Gains Fail: Evaluating Weak-to-Strong Reward Models under Preference Shift
par: Le, Khoi, et autres
Publié: (2026)

A Data-Centric Approach To Generate Faithful and High Quality Patient Summaries with Large Language Models
par: Hegselmann, Stefan, et autres
Publié: (2024)

Weak-to-Strong Compositional Learning from Generative Models for Language-based Object Detection
par: Park, Kwanyong, et autres
Publié: (2024)

Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis
par: Li, Hongkang, et autres
Publié: (2024)

On Giant's Shoulders: Effortless Weak to Strong by Dynamic Logits Fusion
par: Fan, Chenghao, et autres
Publié: (2024)

The Amazing Agent Race: Strong Tool Users, Weak Navigators
par: Kim, Zae Myung, et autres
Publié: (2026)

How Do Latent Reasoning Methods Perform Under Weak and Strong Supervision?
par: Cui, Yingqian, et autres
Publié: (2026)

Volume Optimality in Conformal Prediction with Structured Prediction Sets
par: Gao, Chao, et autres
Publié: (2025)

Zero-to-Strong Generalization: Eliciting Strong Capabilities of Large Language Models Iteratively without Gold Labels
par: Liu, Chaoqun, et autres
Publié: (2024)

Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
par: Chen, Zixiang, et autres
Publié: (2024)

Reranking Laws for Language Generation: A Communication-Theoretic Perspective
par: Farinhas, António, et autres
Publié: (2024)

Selective Weak-to-Strong Generalization
par: Lang, Hao, et autres
Publié: (2025)

A Measure-Theoretic Analysis of Reasoning: Structural Generalization and Approximation Limits
par: Zhang, Yuyang, et autres
Publié: (2026)

Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models
par: Zhou, Zhanhui, et autres
Publié: (2024)

Bias in LLMs as Annotators: The Effect of Party Cues on Labelling Decision by Large Language Models
par: Vera, Sebastian Vallejo, et autres
Publié: (2024)

Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines
par: Li, Yuchen, et autres
Publié: (2024)

DC-W2S: Dual-Consensus Weak-to-Strong Training for Reliable Process Reward Modeling in Biological Reasoning
par: Chan, Chi-Min, et autres
Publié: (2026)

Scaling Reasoning Hop Exposes Weaknesses: Demystifying and Improving Hop Generalization in Large Language Models
par: Li, Zhaoyi, et autres
Publié: (2026)

Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention Models
par: Lee, Chungpa, et autres
Publié: (2026)

Debate Helps Weak-to-Strong Generalization
par: Lang, Hao, et autres
Publié: (2025)

Compact Conformal Subgraphs
par: Gollapudi, Sreenivas, et autres
Publié: (2026)

Compositional Generalization from Learned Skills via CoT Training: A Theoretical and Structural Analysis for Reasoning
par: Yao, Xinhao, et autres
Publié: (2025)

Demystifying Low-Rank Knowledge Distillation in Large Language Models: Convergence, Generalization, and Information-Theoretic Guarantees
par: Soarez, Alberlucia Rafael, et autres
Publié: (2026)

Large Language Models are Powerful Electronic Health Record Encoders
par: Hegselmann, Stefan, et autres
Publié: (2025)

Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models
par: Zhang, Hanlin, et autres
Publié: (2023)

Strong Teacher Not Needed? On Distillation in LLM Pretraining
par: Lu, Taiming, et autres
Publié: (2026)

Numerical Claim Detection in Finance: A New Financial Dataset, Weak-Supervision Model, and Market Analysis
par: Shah, Agam, et autres
Publié: (2024)

Rewarding Intellectual Humility Learning When Not To Answer In Large Language Models
par: Jha, Abha, et autres
Publié: (2026)