← Authors

Shauli Ravfogel

31 papers · 2018–2025 · 8 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird πŸ—ΊοΈ Taxonomy Completionist (72) 🌈 Renaissance Researcher (8) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (10) 🌍 Conference Polyglot (8) πŸƒ Academic Marathon (7) 🀝 Dynamic Duo (22) πŸ”¬ Deep Specialist (11) 🧬 Topic Evolution πŸ† Keyword Champion (5) ❓ The Questioner πŸ“ˆ Trend Setter πŸ—ƒοΈ Keyword Collector (155) πŸ”₯ Unstoppable (8) πŸ’Ž Century Club (31) ⚑ Prolific Year (7)

Conferences

EMNLP (13) ACL (7) NAACL (3) NIPS (3) ICML (2) CONLL (1) ICLR (1) IJCNLP (1)

Top co-authors

Yoav Goldberg (22) Ryan Cotterell (7) Yanai Elazar (6) Hila Gonen (3) Tal Linzen (3) Hillel Taub-Tabib (2) Royi Rassin (2) Jacob Goldberger (2) Anej Svete (2) Mrinmaya Sachan (2)

Keywords

representation learning (8) concept erasure (5) language model (4) agreement prediction (4) bias mitigation (4) neural representation (3) causal inference (3) counterfactual intervention (2) gender bia (2) extractive search (2) linear classifier (2) syntactic structure (2) model interpretability (2) relative clause (2) cross-lingual transfer (2) information extraction (2) transfer learning (2) text-to-image generation (2) neural retrieval (2) structured information (2)

Papers

Intrinsic Test of Unlearning Using Parametric Knowledge Traces EMNLP 2025
A Practical Method for Generating String Counterfactuals NAACL 2025
Gumbel Counterfactual Generation From Language Models ICLR 2025
The Medium Is Not the Message: Deconfounding Document Embeddings via Linear Concept Erasure EMNLP 2025
Language Concept Erasure for Language-invariant Dense Retrieval EMNLP 2024
Representation Surgery: Theory and Practice of Affine Steering ICML 2024
On Affine Homotopy between Language Encoders NIPS 2024
Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment NIPS 2023
LEACE: Perfect linear concept erasure in closed form NIPS 2023
Log-linear Guardedness and its Implications ACL 2023
Conformal Nucleus Sampling ACL 2023
Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation ACL 2023
The Curious Case of Hallucinatory (Un)answerability: Finding Truths in the Hidden States of Over-Confident Large Language Models EMNLP 2023
Guiding LLM to Fool Itself: Automatically Manipulating Machine Reading Comprehension Shortcut Triggers EMNLP 2023
Linear Adversarial Concept Erasure ICML 2022
Adversarial Concept Erasure in Kernel Space EMNLP 2022
DALLE-2 is Seeing Double: Flaws in Word-to-Concept Mapping in Text2Image Models EMNLP 2022
Analyzing Gender Representation in Multilingual Models ACL 2022
BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models ACL 2022
Ab Antiquo: Neural Proto-language Reconstruction NAACL 2021
Contrastive Explanations for Model Interpretability EMNLP 2021
Neural Extractive Search ACL 2021
Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction EMNLP 2021
Neural Extractive Search IJCNLP 2021
Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction CONLL 2021
Unsupervised Distillation of Syntactic Information from Contextualized Word Representations EMNLP 2020
Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection ACL 2020
It’s not Greek to mBERT: Inducing Word-Level Translations from Multilingual BERT EMNLP 2020
The Extraordinary Failure of Complement Coercion Crowdsourcing EMNLP 2020
Studying the Inductive Biases of RNNs with Synthetic Variations of Natural Languages NAACL 2019
Can LSTM Learn to Capture Agreement? The Case of Basque EMNLP 2018