Image de couverture de livre

Self-Improvement in Language Models: The Sharpening Mechanism

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Huang, Audrey, Block, Adam, Foster, Dylan J., Rohatgi, Dhruv, Zhang, Cyril, Simchowitz, Max, Ash, Jordan T., Krishnamurthy, Akshay
Format:	Preprint
Publié:	2024
Sujets:	Artificial Intelligence Computation and Language Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

The Coverage Principle: How Pre-Training Enables Post-Training
par: Chen, Fan, et autres
Publié: (2025)

Representation-Based Exploration for Language Models: From Test-Time to Post-Training
par: Tuyls, Jens, et autres
Publié: (2025)

Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference
par: Golowich, Noah, et autres
Publié: (2026)

Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification
par: Rohatgi, Dhruv, et autres
Publié: (2025)

Is a Good Foundation Necessary for Efficient Reinforcement Learning? The Computational Role of the Base Model in Exploration
par: Foster, Dylan J., et autres
Publié: (2025)

Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment
par: Huang, Audrey, et autres
Publié: (2025)

Can large language models explore in-context?
par: Krishnamurthy, Akshay, et autres
Publié: (2024)

Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization
par: Huang, Audrey, et autres
Publié: (2024)

Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF
par: Xie, Tengyang, et autres
Publié: (2024)

ALAS: Autonomous Learning Agent for Self-Updating Language Models
par: Atreja, Dhruv
Publié: (2025)

EMA Without the Lag: Bias-Corrected Iterate Averaging Schemes
par: Block, Adam, et autres
Publié: (2025)

Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning
par: Foster, Dylan J., et autres
Publié: (2024)

GaussMark: A Practical Approach for Structural Watermarking of Language Models
par: Block, Adam, et autres
Publié: (2025)

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

A Unifying View of Coverage in Linear Off-Policy Evaluation
par: Amortila, Philip, et autres
Publié: (2026)

Self-Evolved Preference Optimization for Enhancing Mathematical Reasoning in Small Language Models
par: Singh, Joykirat, et autres
Publié: (2025)

Analyzing And Editing Inner Mechanisms Of Backdoored Language Models
par: Lamparth, Max, et autres
Publié: (2023)

Learning Hidden Markov Models Using Conditional Samples
par: Kakade, Sham M., et autres
Publié: (2023)

Necessary and Sufficient Oracles: Toward a Computational Taxonomy For Reinforcement Learning
par: Rohatgi, Dhruv, et autres
Publié: (2025)

Reinforcement Learning under Latent Dynamics: Toward Statistical and Algorithmic Modularity
par: Amortila, Philip, et autres
Publié: (2024)

Self-Generated Critiques Boost Reward Modeling for Language Models
par: Yu, Yue, et autres
Publié: (2024)

Policy Improvement using Language Feedback Models
par: Zhong, Victor, et autres
Publié: (2024)

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

An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models
par: Bhatt, Gantavya, et autres
Publié: (2024)

LLMs as High-Dimensional Nonlinear Autoregressive Models with Attention: Training, Alignment and Inference
par: Krishnamurthy, Vikram
Publié: (2026)

Pioneer Agent: Continual Improvement of Small Language Models in Production
par: Atreja, Dhruv, et autres
Publié: (2026)

Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement
par: Wang, Xiyao, et autres
Publié: (2024)

Language Models Represent Space and Time
par: Gurnee, Wes, et autres
Publié: (2023)

Uncertainty Quantification for Language Models: A Suite of Black-Box, White-Box, LLM Judge, and Ensemble Scorers
par: Bouchard, Dylan, et autres
Publié: (2025)

Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling
par: Ding, Yiwen, et autres
Publié: (2024)

Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains
par: Subramaniam, Vighnesh, et autres
Publié: (2025)

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

Language Models Use Trigonometry to Do Addition
par: Kantamneni, Subhash, et autres
Publié: (2025)

Private Language Models via Truncated Laplacian Mechanism
par: Huang, Tianhao, et autres
Publié: (2024)

Mitigating Distribution Sharpening in Math RLVR via Distribution-Aligned Hint Synthesis and Backward Hint Annealing
par: Xie, Pei-Xi, et autres
Publié: (2026)

Parallax: Parameterized Local Linear Attention for Language Modeling
par: Zuo, Yifei, et autres
Publié: (2026)

Dynamic Strategy Planning for Efficient Question Answering with Large Language Models
par: Parekh, Tanmay, et autres
Publié: (2024)

Smoothed Online Learning for Prediction in Piecewise Affine Systems
par: Block, Adam, et autres
Publié: (2023)

Oracle-Efficient Smoothed Online Learning for Piecewise Continuous Decision Making
par: Block, Adam, et autres
Publié: (2023)

Method-Based Reasoning for Large Language Models: Extraction, Reuse, and Continuous Improvement
par: Su, Hong
Publié: (2025)