Imagen de Portada

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Olmo, Jeffrey, Wilson, Jared, Forsey, Max, Hepner, Bryce, Howe, Thomas Vin, Wingate, David
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Language models struggle with compartmentalization
por: Howe, Thomas Vincent, et al.
Publicado: (2026)

Arti-"fickle" Intelligence: Using LLMs as a Tool for Inference in the Political and Social Sciences
por: Argyle, Lisa P., et al.
Publicado: (2025)

Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models
por: Karvonen, Adam, et al.
Publicado: (2024)

Scaling Law with Learning Rate Annealing
por: Tissue, Howe, et al.
Publicado: (2024)

Share Your Attention: Transformer Weight Sharing via Matrix-based Dictionary Learning
por: Zhussip, Magauiya, et al.
Publicado: (2025)

Low-Cost Generation and Evaluation of Dictionary Example Sentences
por: Cai, Bill, et al.
Publicado: (2024)

Diagnosing Transformers: Illuminating Feature Spaces for Clinical Decision-Making
por: Hsu, Aliyah R., et al.
Publicado: (2023)

BARE: Leveraging Base Language Models for Few-Shot Synthetic Data Generation
por: Zhu, Alan, et al.
Publicado: (2025)

Learning Dynamics in Continual Pre-Training for Large Language Models
por: Wang, Xingjin, et al.
Publicado: (2025)

Plan Optimization to Bilingual Dictionary Induction for Low-Resource Language Families
por: Nasution, Arbi Haza, et al.
Publicado: (2020)

Improving Dictionary Learning with Gated Sparse Autoencoders
por: Rajamanoharan, Senthooran, et al.
Publicado: (2024)

StylOch at PAN: Gradient-Boosted Trees with Frequency-Based Stylometric Features
por: Ochab, Jeremi K., et al.
Publicado: (2025)

Dictionary Learning: The Complexity of Learning Sparse Superposed Features with Feedback
por: Kumar, Akash
Publicado: (2025)

Enhancing Clinical Documentation with Synthetic Data: Leveraging Generative Models for Improved Accuracy
por: Biswas, Anjanava, et al.
Publicado: (2024)

Beyond Gradient and Priors in Privacy Attacks: Leveraging Pooler Layer Inputs of Language Models in Federated Learning
por: Li, Jianwei, et al.
Publicado: (2023)

Improving Steering Vectors by Targeting Sparse Autoencoder Features
por: Chalnev, Sviatoslav, et al.
Publicado: (2024)

Language Agents for Hypothesis-driven Clinical Decision Making with Reinforcement Learning
por: Bani-Harouni, David, et al.
Publicado: (2025)

ScenicProver: A Framework for Compositional Probabilistic Verification of Learning-Enabled Systems
por: Vin, Eric, et al.
Publicado: (2025)

Improving LoRA with Variational Learning
por: Cong, Bai, et al.
Publicado: (2025)

Check Your LLM's Secret Dictionary! Five Lines of Code Reveal What Your LLM Learned (Including What It Shouldn't Have)
por: Miyashita, Hisashi
Publicado: (2026)

Dense SAE Latents Are Features, Not Bugs
por: Sun, Xiaoqing, et al.
Publicado: (2025)

Chasing COMET: Leveraging Minimum Bayes Risk Decoding for Self-Improving Machine Translation
por: Guttmann, Kamil, et al.
Publicado: (2024)

Domain2Vec: Vectorizing Datasets to Find the Optimal Data Mixture without Training
por: Zhang, Mozhi, et al.
Publicado: (2025)

Enhancing Antibiotic Stewardship using a Natural Language Approach for Better Feature Representation
por: Lee, Simon A., et al.
Publicado: (2024)

Advancing Arabic Reverse Dictionary Systems: A Transformer-Based Approach with Dataset Construction Guidelines
por: Sibaee, Serry, et al.
Publicado: (2025)

Token-Efficient Leverage Learning in Large Language Models
por: Zeng, Yuanhao, et al.
Publicado: (2024)

Feature Hedging: Correlated Features Break Narrow Sparse Autoencoders
por: Chanin, David, et al.
Publicado: (2025)

Do pretrained Transformers Learn In-Context by Gradient Descent?
por: Shen, Lingfeng, et al.
Publicado: (2023)

Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
por: Braun, Dan, et al.
Publicado: (2024)

Curiosity-Critic: Cumulative Prediction Error Improvement as a Tractable Intrinsic Reward for World Model Training
por: Bhaskara, Vin, et al.
Publicado: (2026)

Model Merging by Uncertainty-Based Gradient Matching
por: Daheim, Nico, et al.
Publicado: (2023)

Learning to Interpret Weight Differences in Language Models
por: Goel, Avichal, et al.
Publicado: (2025)

Ask more, know better: Reinforce-Learned Prompt Questions for Decision Making with Large Language Models
por: Yan, Xue, et al.
Publicado: (2023)

Quantifying and Improving the Robustness of Retrieval-Augmented Language Models Against Spurious Features in Grounding Data
por: Yang, Shiping, et al.
Publicado: (2025)

Linear-Time Demonstration Selection for In-Context Learning via Gradient Estimation
por: Zhang, Ziniu, et al.
Publicado: (2025)

GradAlign: Gradient-Aligned Data Selection for LLM Reinforcement Learning
por: Yang, Ningyuan, et al.
Publicado: (2026)

FLUID-LLM: Learning Computational Fluid Dynamics with Spatiotemporal-aware Large Language Models
por: Zhu, Max, et al.
Publicado: (2024)

Why Larger Language Models Do In-context Learning Differently?
por: Shi, Zhenmei, et al.
Publicado: (2024)

Sparse Autoencoder Features for Classifications and Transferability
por: Gallifant, Jack, et al.
Publicado: (2025)

Beyond Label Attention: Transparency in Language Models for Automated Medical Coding via Dictionary Learning
por: Wu, John, et al.
Publicado: (2024)