:: Library Catalog

Cover Image

Saved in:

Bibliographic Details
Main Authors:	Lee, Andrew, Viégas, Fernanda, Wattenberg, Martin
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	https://arxiv.org/abs/2605.09967
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Shared Global and Local Geometry of Language Model Embeddings
by: Lee, Andrew, et al.
Published: (2025)

Decomposing Query-Key Feature Interactions Using Contrastive Covariances
by: Lee, Andrew, et al.
Published: (2026)

Relational Composition in Neural Networks: A Survey and Call to Action
by: Wattenberg, Martin, et al.
Published: (2024)

Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner
by: Li, Kenneth, et al.
Published: (2024)

The Geometry of Self-Verification in a Task-Specific Reasoning Model
by: Lee, Andrew, et al.
Published: (2025)

Why Can't Transformers Learn Multiplication? Reverse-Engineering Reveals Long-Range Dependency Pitfalls
by: Bai, Xiaoyan, et al.
Published: (2025)

When Bad Data Leads to Good Models
by: Li, Kenneth, et al.
Published: (2025)

Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task
by: Li, Kenneth, et al.
Published: (2022)

Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
by: Li, Kenneth, et al.
Published: (2023)

Chronotome: Real-Time Topic Modeling for Streaming Embedding Spaces
by: Lim, Matte, et al.
Published: (2025)

Measuring and Controlling Instruction (In)Stability in Language Model Dialogs
by: Li, Kenneth, et al.
Published: (2024)

Story Ribbons: Reimagining Storyline Visualizations with Large Language Models
by: Yeh, Catherine, et al.
Published: (2025)

What Does it Mean for a Neural Network to Learn a "World Model"?
by: Li, Kenneth, et al.
Published: (2025)

Q-Probe: A Lightweight Approach to Reward Maximization for Language Models
by: Li, Kenneth, et al.
Published: (2024)

ICLR: In-Context Learning of Representations
by: Park, Core Francisco, et al.
Published: (2024)

Attention-based Iterative Decomposition for Tensor Product Representation
by: Park, Taewon, et al.
Published: (2024)

Optimal Representation Size: High-Dimensional Analysis of Pretraining and Linear Probing
by: Njaradi, Valentina, et al.
Published: (2026)

Learning Shared Representations for Multi-Task Linear Bandits
by: Lin, Jiabin, et al.
Published: (2026)

Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior
by: Wurgaft, Daniel, et al.
Published: (2026)

Graph Edge Representation via Tensor Product Graph Convolutional Representation
by: Jiang, Bo, et al.
Published: (2024)

Does visualization help AI understand data?
by: Li, Victoria R., et al.
Published: (2025)

Semantic Convergence: Investigating Shared Representations Across Scaled LLMs
by: Son, Daniel, et al.
Published: (2025)

On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations
by: Xiong, Guojun, et al.
Published: (2024)

Towards Sampling Data Structures for Tensor Products in Turnstile Streams
by: Song, Zhao, et al.
Published: (2025)

Representation Alignment Rests on Linear Structure
by: Bangachev, Kiril, et al.
Published: (2026)

Contrastive Learning of Shared Spatiotemporal EEG Representations Across Individuals for Naturalistic Neuroscience
by: Shen, Xinke, et al.
Published: (2024)

Gradient-Direction Sensitivity Reveals Linear-Centroid Coupling Hidden by Optimizer Trajectories
by: Xu, Yongzhong
Published: (2026)

Tensor Completion with Nearly Linear Samples Given Weak Side Information
by: Yu, Christina Lee, et al.
Published: (2020)

Priors in Time: Missing Inductive Biases for Language Model Interpretability
by: Lubana, Ekdeep Singh, et al.
Published: (2025)

Rhetorical Questions in LLM Representations: A Linear Probing Study
by: Yao, Louie Hong, et al.
Published: (2026)

E2Former: An Efficient and Equivariant Transformer with Linear-Scaling Tensor Products
by: Li, Yunyang, et al.
Published: (2025)

Fully Distributed, Flexible Compositional Visual Representations via Soft Tensor Products
by: Sun, Bethia, et al.
Published: (2024)

A Single Direction of Truth: An Observer Model's Linear Residual Probe Exposes and Steers Contextual Hallucinations
by: O'Neill, Charles, et al.
Published: (2025)

Dynamics Reveals Structure: Challenging the Linear Propagation Assumption
by: Chang, Hoyeon, et al.
Published: (2026)

Learning Representations for Reasoning: Generalizing Across Diverse Structures
by: Zhu, Zhaocheng
Published: (2024)

Structured Unitary Tensor Network Representations for Circuit-Efficient Quantum Data Encoding
by: Lin, Guang, et al.
Published: (2026)

Near-optimal and Efficient First-Order Algorithm for Multi-Task Learning with Shared Linear Representation
by: Ding, Shihong, et al.
Published: (2026)

Learning Fine-grained Parameter Sharing via Sparse Tensor Decomposition
by: Üyük, Cem, et al.
Published: (2024)

Shared Parameter Subspaces and Cross-Task Linearity in Emergently Misaligned Behavior
by: Arturi, Daniel Aarao Reis, et al.
Published: (2025)

Can Interpretation Predict Behavior on Unseen Data?
by: Li, Victoria R., et al.
Published: (2025)