Cover Image

A Theoretical Understanding of Self-Correction through In-context Alignment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Yifei, Wu, Yuyang, Wei, Zeming, Jegelka, Stefanie, Wang, Yisen
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

When More is Less: Understanding Chain-of-Thought Length in LLMs
by: Wu, Yuyang, et al.
Published: (2025)

What is Wrong with Perplexity for Long-context Language Modeling?
by: Fang, Lizhe, et al.
Published: (2024)

Advancing LLM Safe Alignment with Safety Representation Ranking
by: Du, Tianqi, et al.
Published: (2025)

Long-Short Alignment for Effective Long-Context Modeling in LLMs
by: Du, Tianqi, et al.
Published: (2025)

Understanding the Role of Equivariance in Self-supervised Learning
by: Wang, Yifei, et al.
Published: (2024)

Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations
by: Wei, Zeming, et al.
Published: (2023)

Look Ahead or Look Around? A Theoretical Comparison Between Autoregressive and Masked Pretraining
by: Zhang, Qi, et al.
Published: (2024)

Fight Back Against Jailbreaking via Prompt Adversarial Tuning
by: Mo, Yichuan, et al.
Published: (2024)

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval
by: Chen, Taiye, et al.
Published: (2025)

How to Craft Backdoors with Unlabeled Data Alone?
by: Wang, Yifei, et al.
Published: (2024)

A Canonicalization Perspective on Invariant and Equivariant Learning
by: Ma, George, et al.
Published: (2024)

In-Context Symmetries: Self-Supervised Learning through Contextual World Models
by: Gupta, Sharut, et al.
Published: (2024)

Identifying and Understanding Cross-Class Features in Adversarial Training
by: Wei, Zeming, et al.
Published: (2025)

LANPO: Bootstrapping Language and Numerical Feedback for Reinforcement Learning in LLMs
by: Li, Ang, et al.
Published: (2025)

G1: Teaching LLMs to Reason on Graphs with Reinforcement Learning
by: Guo, Xiaojun, et al.
Published: (2025)

Polynomial Regression as a Task for Understanding In-context Learning Through Finetuning and Alignment
by: Wilcoxson, Max, et al.
Published: (2024)

Utilizing and Calibrating Hindsight Process Rewards via Reinforcement with Mutual Information Self-Evaluation
by: Yao, Jiashu, et al.
Published: (2026)

Towards Analyzing and Understanding the Limitations of VAPO: A Theoretical Perspective
by: Shao, Jintian, et al.
Published: (2025)

On the Emergence of Position Bias in Transformers
by: Wu, Xinyi, et al.
Published: (2025)

Learning from Failures: Understanding LLM Alignment through Failure-Aware Inverse RL
by: Patel, Nyal, et al.
Published: (2025)

Multilingual Safety Alignment via Self-Distillation
by: Qin, Ruiyang, et al.
Published: (2026)

Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness
by: Zhang, Qi, et al.
Published: (2024)

On the Limits of Sparse Autoencoders: A Theoretical Framework and Reweighted Remedy
by: Cui, Jingyi, et al.
Published: (2025)

Towards Understanding the Relationship between In-context Learning and Compositional Generalization
by: Han, Sungjun, et al.
Published: (2024)

Benefits and Pitfalls of Reinforcement Learning for Language Model Planning: A Theoretical Perspective
by: Wang, Siwei, et al.
Published: (2025)

Is Free Self-Alignment Possible?
by: Adila, Dyah, et al.
Published: (2024)

On the Convergence of Moral Self-Correction in Large Language Models
by: Liu, Guangliang, et al.
Published: (2025)

A Measure-Theoretic Analysis of Reasoning: Structural Generalization and Approximation Limits
by: Zhang, Yuyang, et al.
Published: (2026)

Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment
by: Yin, Yueqin, et al.
Published: (2024)

Learning to Align, Aligning to Learn: A Unified Approach for Self-Optimized Alignment
by: Wang, Haowen, et al.
Published: (2025)

MLP Fusion: Towards Efficient Fine-tuning of Dense and Mixture-of-Experts Language Models
by: Ai, Mengting, et al.
Published: (2023)

Theoretical Understanding of In-Context Learning in Shallow Transformers with Unstructured Data
by: Xing, Yue, et al.
Published: (2024)

Can In-context Learning Really Generalize to Out-of-distribution Tasks?
by: Wang, Qixun, et al.
Published: (2024)

CrossTrafficLLM: A Human-Centric Framework for Interpretable Traffic Intelligence via Large Language Model
by: Du, Zeming, et al.
Published: (2025)

Efficient Post-Training Pruning of Large Language Models with Statistical Correction
by: Yu, Peiqi, et al.
Published: (2026)

Self-Taught Self-Correction for Small Language Models
by: Moskvoretskii, Viktor, et al.
Published: (2025)

Theoretical Limits of Language Model Alignment
by: Paes, Lucas Monteiro, et al.
Published: (2026)

Breaking through the learning plateaus of in-context learning in Transformer
by: Fu, Jingwen, et al.
Published: (2023)

Gating is Weighting: Understanding Gated Linear Attention through In-context Learning
by: Li, Yingcong, et al.
Published: (2025)

Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics
by: Zhu, Hanlin, et al.
Published: (2024)