Imagen de Portada

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Bello, Femi, Das, Anubrata, Zeng, Fanzhi, Yin, Fangcong, Leqi, Liu
Formato:	Preprint
Publicado:	2025
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

Curriculum Learning-Guided Progressive Distillation in Large Language Models
por: Cao, Jincheng, et al.
Publicado: (2026)

The Linear Representation Hypothesis and the Geometry of Large Language Models
por: Park, Kiho, et al.
Publicado: (2023)

Compositional Steering of Large Language Models with Steering Tokens
por: Radevski, Gorjan, et al.
Publicado: (2026)

Prompting Fairness: Integrating Causality to Debias Large Language Models
por: Li, Jingling, et al.
Publicado: (2024)

A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement
por: Yuan, Hui, et al.
Publicado: (2024)

Hypothesis Generation with Large Language Models
por: Zhou, Yangqiaoyu, et al.
Publicado: (2024)

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

CARE-RFT: Confidence-Anchored Reinforcement Finetuning for Reliable Reasoning in Large Language Models
por: Li, Shuozhe, et al.
Publicado: (2026)

Personalized Language Modeling from Personalized Human Feedback
por: Li, Xinyu, et al.
Publicado: (2024)

Beyond Linear Steering: Unified Multi-Attribute Control for Language Models
por: Oozeer, Narmeen, et al.
Publicado: (2025)

The Consistency Hypothesis in Uncertainty Quantification for Large Language Models
por: Xiao, Quan, et al.
Publicado: (2025)

Steering Large Language Models for Machine Translation Personalization
por: Scalena, Daniel, et al.
Publicado: (2025)

COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics
por: Sharma, Kartik, et al.
Publicado: (2026)

Learning Composable Chains-of-Thought
por: Yin, Fangcong, et al.
Publicado: (2025)

SteeringSafety: A Systematic Safety Evaluation Framework of Representation Steering in LLMs
por: Siu, Vincent, et al.
Publicado: (2025)

FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models
por: Weng, Zixuan, et al.
Publicado: (2026)

Mitigating Overthinking in Large Reasoning Models via Manifold Steering
por: Huang, Yao, et al.
Publicado: (2025)

Extracting and Encoding: Leveraging Large Language Models and Medical Knowledge to Enhance Radiological Text Representation
por: Messina, Pablo, et al.
Publicado: (2024)

Understanding Unreliability of Steering Vectors in Language Models: Geometric Predictors and the Limits of Linear Approximations
por: Braun, Joschka
Publicado: (2026)

Multi-property Steering of Large Language Models with Dynamic Activation Composition
por: Scalena, Daniel, et al.
Publicado: (2024)

Interpretable Steering of Large Language Models with Feature Guided Activation Additions
por: Soo, Samuel, et al.
Publicado: (2025)

ContextFocus: Activation Steering for Contextual Faithfulness in Large Language Models
por: Anand, Nikhil, et al.
Publicado: (2026)

What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal
por: Cheng, Stephen, et al.
Publicado: (2026)

How Many Features Can a Language Model Store Under the Linear Representation Hypothesis?
por: Garg, Nikhil, et al.
Publicado: (2026)

Leveraging Group Relative Policy Optimization to Advance Large Language Models in Traditional Chinese Medicine
por: Xie, Jiacheng, et al.
Publicado: (2025)

Leveraging Large Language Models for Web Scraping
por: Ahluwalia, Aman, et al.
Publicado: (2024)

Steering Large Reasoning Models towards Concise Reasoning via Flow Matching
por: Li, Yawei, et al.
Publicado: (2026)

All Language Models Large and Small
por: Chen, Zhixun, et al.
Publicado: (2024)

Linear Chain Transformation: Expanding Optimization Dynamics for Fine-Tuning Large Language Models
por: Wang, Yulong, et al.
Publicado: (2024)

Word Embeddings Are Steers for Language Models
por: Han, Chi, et al.
Publicado: (2023)

Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models
por: Zhou, Zhanhui, et al.
Publicado: (2024)

Hypothesis Search: Inductive Reasoning with Language Models
por: Wang, Ruocheng, et al.
Publicado: (2023)

PMPO: Probabilistic Metric Prompt Optimization for Small and Large Language Models
por: Zhao, Chenzhuo, et al.
Publicado: (2025)

Equivalent Linear Mappings of Large Language Models
por: Golden, James R.
Publicado: (2025)

Endogenous Resistance to Activation Steering in Language Models
por: McKenzie, Alex, et al.
Publicado: (2026)

Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry
por: Li, Zhuochun, et al.
Publicado: (2026)

SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models
por: Yang, Yu, et al.
Publicado: (2024)

Improving Large Models with Small models: Lower Costs and Better Performance
por: Chen, Dong, et al.
Publicado: (2024)

Leveraging Large Language Models for Solving Rare MIP Challenges
por: Wang, Teng, et al.
Publicado: (2024)

Analyzing the Role of Semantic Representations in the Era of Large Language Models
por: Jin, Zhijing, et al.
Publicado: (2024)