Image de couverture de livre

Transferring Linear Features Across Language Models With Model Stitching

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Alan, Merullo, Jack, Stolfo, Alessandro, Pavlick, Ellie
Format:	Preprint
Publié:	2025
Sujets:	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

Circuit Component Reuse Across Tasks in Transformer Language Models
par: Merullo, Jack, et autres
Publié: (2023)

Language Models Implement Simple Word2Vec-style Vector Arithmetic
par: Merullo, Jack, et autres
Publié: (2023)

Dual Process Learning: Controlling Use of In-Context vs. In-Weights Strategies with Weight Forgetting
par: Anand, Suraj, et autres
Publié: (2024)

Talking Heads: Understanding Inter-layer Communication in Transformer Language Models
par: Merullo, Jack, et autres
Publié: (2024)

How Do Vision-Language Models Process Conflicting Information Across Modalities?
par: Hua, Tianze, et autres
Publié: (2025)

$100K or 100 Days: Trade-offs when Pre-Training with Academic Resources
par: Khandelwal, Apoorv, et autres
Publié: (2024)

Does Training on Synthetic Data Make Models Less Robust?
par: Zhang, Lingze, et autres
Publié: (2025)

Groundedness in Retrieval-augmented Long-form Generation: An Empirical Study
par: Stolfo, Alessandro
Publié: (2024)

Improving Instruction-Following in Language Models through Activation Steering
par: Stolfo, Alessandro, et autres
Publié: (2024)

I Have No Mouth, and I Must Rhyme: Uncovering Internal Phonetic Representations in LLaMA 3.2
par: McLaughlin, Oliver, et autres
Publié: (2025)

Confidence Regulation Neurons in Language Models
par: Stolfo, Alessandro, et autres
Publié: (2024)

From Memorization to Reasoning in the Spectrum of Loss Curvature
par: Merullo, Jack, et autres
Publié: (2025)

How Do Language Models Compose Functions?
par: Khandelwal, Apoorv, et autres
Publié: (2025)

Dense SAE Latents Are Features, Not Bugs
par: Sun, Xiaoqing, et autres
Publié: (2025)

Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners?
par: Opedal, Andreas, et autres
Publié: (2024)

Born a Transformer -- Always a Transformer? On the Effect of Pretraining on Architectural Abilities
par: Jobanputra, Mayank, et autres
Publié: (2025)

What is an "Abstract Reasoner"? Revisiting Experiments and Arguments about Large Language Models
par: Yun, Tian, et autres
Publié: (2025)

Feature Alignment and Representation Transfer in Knowledge Distillation for Large Language Models
par: Yang, Junjie, et autres
Publié: (2025)

Does CLIP Bind Concepts? Probing Compositionality in Large Image Models
par: Lewis, Martha, et autres
Publié: (2022)

Source-Modality Monitoring in Vision-Language Models
par: Hua, Etha Tianze, et autres
Publié: (2026)

mOthello: When Do Cross-Lingual Representation Alignment and Cross-Lingual Transfer Emerge in Multilingual Models?
par: Hua, Tianze, et autres
Publié: (2024)

R-Stitch: Dynamic Trajectory Stitching for Efficient Reasoning
par: Chen, Zhuokun, et autres
Publié: (2025)

Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought
par: Boppana, Siddharth, et autres
Publié: (2026)

Atlas-Alignment: Making Interpretability Transferable Across Language Models
par: Puri, Bruno, et autres
Publié: (2025)

On Linear Representations and Pretraining Data Frequency in Language Models
par: Merullo, Jack, et autres
Publié: (2025)

Sparse Autoencoder Features for Classifications and Transferability
par: Gallifant, Jack, et autres
Publié: (2025)

Probing for Arithmetic Errors in Language Models
par: Sun, Yucheng, et autres
Publié: (2025)

Linear Dynamics in the RLVR Training of Large Language Models
par: Wang, Tianle, et autres
Publié: (2026)

Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders
par: Lan, Michael, et autres
Publié: (2024)

Replacing Language Model for Style Transfer
par: Cheng, Pengyu, et autres
Publié: (2022)

On the Origins of Linear Representations in Large Language Models
par: Jiang, Yibo, et autres
Publié: (2024)

Transfer Learning for Finetuning Large Language Models
par: Strangmann, Tobias, et autres
Publié: (2024)

Generalizing Large Language Model Usability Across Resource-Constrained
par: Tsai, Yun-Da
Publié: (2025)

Can Large Language Models Generalize Procedures Across Representations?
par: Lin, Fangru, et autres
Publié: (2026)

Invariant Features in Language Models: Geometric Characterization and Model Attribution
par: Dasgupta, Agnibh, et autres
Publié: (2026)

Persona Vectors: Monitoring and Controlling Character Traits in Language Models
par: Chen, Runjin, et autres
Publié: (2025)

Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic
par: He, Yifei, et autres
Publié: (2024)

LoLCATs: On Low-Rank Linearizing of Large Language Models
par: Zhang, Michael, et autres
Publié: (2024)

Rotary Offset Features in Large Language Models
par: Jonasson, André
Publié: (2025)

Can LLMs subtract numbers?
par: Jobanputra, Mayank, et autres
Publié: (2025)