Shauli Ravfogel
- Papers
- 13
Cite
Notes
Only stored in your browser.
Authored papers
13From Directions to Regions: Decomposing Activations in Language Models via Local Geometry
arXiv 2026
The Truthfulness Spectrum Hypothesis
arXiv 2026
Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces
arXiv 2024
Gumbel Counterfactual Generation From Language Models
arXiv 2024
A Practical Method for Generating String Counterfactuals
arXiv 2024
The Role of Language Imbalance in Cross-lingual Generalisation: Insights from Cloned Language Experiments
arXiv 2024
Representation Surgery: Theory and Practice of Affine Steering
arXiv 2024
LEACE: Perfect linear concept erasure in closed form
NeurIPS 2023 11
Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment
linguistic-binding-in-diffusion-models
Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation
arXiv 2023
Linear Adversarial Concept Erasure
arXiv 2022
BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models
ACL 2022 5
Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection
null-it-out-guarding-protected-attributes-by-1
Affiliations
Frequent co-authors
10from 13 papers