:: Library Catalog

Cover Image

Saved in:

Bibliographic Details
Main Authors:	Holstege, Floris, Ravfogel, Shauli, Wouters, Bram
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	https://arxiv.org/abs/2506.10703
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Removing Spurious Concepts from Neural Network Representations via Joint Subspace Estimation
by: Holstege, Floris, et al.
Published: (2023)

Optimizing importance weighting in the presence of sub-population shifts
by: Holstege, Floris, et al.
Published: (2024)

Linear Adversarial Concept Erasure
by: Ravfogel, Shauli, et al.
Published: (2022)

Kernelized Concept Erasure
by: Ravfogel, Shauli, et al.
Published: (2022)

Discrete Diffusion Models Exploit Asymmetry to Solve Lookahead Planning Tasks
by: Trainin, Itamar, et al.
Published: (2026)

Log-linear Guardedness and its Implications
by: Ravfogel, Shauli, et al.
Published: (2022)

BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models
by: Ben-Zaken, Elad, et al.
Published: (2021)

The Truthfulness Spectrum Hypothesis
by: Ying, Zhuofan Josh, et al.
Published: (2026)

Gumbel Counterfactual Generation From Language Models
by: Ravfogel, Shauli, et al.
Published: (2024)

A Practical Method for Generating String Counterfactuals
by: Avitan, Matan, et al.
Published: (2024)

Diversity Over Quantity: A Lesson From Few Shot Relation Classification
by: Cohen, Amir DN, et al.
Published: (2024)

The Role of Language Imbalance in Cross-lingual Generalisation: Insights from Cloned Language Experiments
by: Schäfer, Anton, et al.
Published: (2024)

Description-Based Text Similarity
by: Ravfogel, Shauli, et al.
Published: (2023)

Representation Surgery: Theory and Practice of Affine Steering
by: Singh, Shashwat, et al.
Published: (2024)

LEACE: Perfect linear concept erasure in closed form
by: Belrose, Nora, et al.
Published: (2023)

Auditing a Dutch Public Sector Risk Profiling Algorithm Using an Unsupervised Bias Detection Tool
by: Holstege, Floris, et al.
Published: (2025)

The Medium Is Not the Message: Deconfounding Document Embeddings via Linear Concept Erasure
by: Fan, Yu, et al.
Published: (2025)

Can LLMs Introspect? A Reality Check
by: Singh, Shashwat, et al.
Published: (2026)

From Features to Structure: Task-Aware Graph Construction for Relational and Tabular Learning with GNNs
by: Cucumides, Tamara, et al.
Published: (2025)

Emergence of Linear Truth Encodings in Language Models
by: Ravfogel, Shauli, et al.
Published: (2025)

On Affine Homotopy between Language Encoders
by: Chan, Robin SM, et al.
Published: (2024)

Selecting Decision-Relevant Concepts in Reinforcement Learning
by: Raman, Naveen, et al.
Published: (2026)

State over Tokens: Characterizing the Role of Reasoning Tokens
by: Levy, Mosh, et al.
Published: (2025)

Geometric Factual Recall in Transformers
by: Ravfogel, Shauli, et al.
Published: (2026)

Mechanism of Task-oriented Information Removal in In-context Learning
by: Cho, Hakaze, et al.
Published: (2025)

Concept Gradient: Concept-based Interpretation Without Linear Assumption
by: Bai, Andrew, et al.
Published: (2022)

Counterfactual Explanations Under Concept Drift
by: Kostrzewa, Marcin, et al.
Published: (2026)

Certified Data Removal Under High-dimensional Settings
by: Zou, Haolin, et al.
Published: (2025)

Grables: Tabular Learning Beyond Independent Rows
by: Cucumides, Tamara, et al.
Published: (2026)

A note on the VC dimension of 1-dimensional GNNs
by: Daniëls, Noah, et al.
Published: (2024)

Scalable Topology-Preserving Graph Coarsening: Concepts and Algorithms
by: Wu, Xiang, et al.
Published: (2026)

Task Relevance Is Not Local Replaceability: A Two-Axis View of Channel Information
by: Safaai, Houman, et al.
Published: (2026)

Beyond Single Embeddings: Capturing Diverse Targets with Multi-Query Retrieval
by: Chen, Hung-Ting, et al.
Published: (2025)

Reward-Relevance-Filtered Linear Offline Reinforcement Learning
by: Zhou, Angela
Published: (2024)

Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models?
by: Tsai, Yu-Lin, et al.
Published: (2023)

Debugging Concept Bottleneck Models through Removal and Retraining
by: Enouen, Eric, et al.
Published: (2025)

Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient
by: Wu, Yongliang, et al.
Published: (2024)

Optimizing watermarks for large language models
by: Wouters, Bram
Published: (2023)

Learning Counterfactual Outcomes Under Rank Preservation
by: Wu, Peng, et al.
Published: (2025)

From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation
by: Achtibat, Reduan, et al.
Published: (2022)