Shauli Ravfogel

80 papers A* 12B 1Journal 50Unranked 16
YearRankTypeTitle / Venue / Authors
2026 J jnl
Discrete Diffusion Models Exploit Asymmetry to Solve Lookahead Planning Tasks.
CoRR
Itamar Trainin, Shauli Ravfogel, Omri Abend, Amir Feder
2026 J jnl
From Directions to Regions: Decomposing Activations in Language Models via Local Geometry.
CoRR
Or Shafran, Shaked Ronen, Omri Fahn, Shauli Ravfogel, Atticus Geiger, Mor Geva
2026 J jnl
The Truthfulness Spectrum Hypothesis.
CoRR
Zhuofan Josh Ying, Shauli Ravfogel, Nikolaus Kriegeskorte, Peter Hase
2025 — conf
A Practical Method for Generating String Counterfactuals.
NAACL (Findings)
Matan Avitan, Ryan Cotterell, Yoav Goldberg, Shauli Ravfogel
2025 J jnl
Beyond Single Embeddings: Capturing Diverse Targets with Multi-Query Retrieval.
CoRR
Hung-Ting Chen, Xiang Liu, Shauli Ravfogel, Eunsol Choi
2025 J jnl
Emergence of Linear Truth Encodings in Language Models.
CoRR
Shauli Ravfogel, Gilad Yehudai, Tal Linzen, Joan Bruna, Alberto Bietti
2025 A* conf
Gumbel Counterfactual Generation From Language Models.
ICLR
Shauli Ravfogel, Anej Svete, Vésteinn Snæbjarnarson, Ryan Cotterell
2025 J jnl
IQ Test for LLMs: An Evaluation Framework for Uncovering Core Skills in LLMs.
CoRR
Aviya Maimon, Amir David Nissan Cohen, Gal Vishne, Shauli Ravfogel, Reut Tsarfaty
2025 A* conf
Intrinsic Test of Unlearning Using Parametric Knowledge Traces.
EMNLP
Yihuai Hong, Lei Yu, Haiqin Yang, Shauli Ravfogel, Mor Geva
2025 J jnl
Preserving Task-Relevant Information Under Linear Concept Removal.
CoRR
Floris Holstege, Shauli Ravfogel, Bram Wouters
2025 J jnl
RELIC: Evaluating Compositional Instruction Following via Language Recognition.
CoRR
Jackson Petty, Michael Y. Hu, Wentao Wang, Shauli Ravfogel, William Merrill, Tal Linzen
2025 J jnl
State over Tokens: Characterizing the Role of Reasoning Tokens.
CoRR
Mosh Levy, Zohar Elyoseph, Shauli Ravfogel, Yoav Goldberg
2025 A* conf
The Medium Is Not the Message: Deconfounding Document Embeddings via Linear Concept Erasure.
EMNLP
Yu Fan, Yang Tian, Shauli Ravfogel, Mrinmaya Sachan, Elliott Ash, Alexander Miserlis Hoyle
2025 J jnl
The Medium Is Not the Message: Deconfounding Text Embeddings via Linear Concept Erasure.
CoRR
Yu Fan, Yang Tian, Shauli Ravfogel, Mrinmaya Sachan, Elliott Ash, Alexander Miserlis Hoyle
2024 J jnl
Counterfactual Generation from Language Models.
CoRR
Shauli Ravfogel, Anej Svete, Vésteinn Snæbjarnarson, Ryan Cotterell
2024 J jnl
Diversity Over Quantity: A Lesson From Few Shot Relation Classification.
CoRR
Amir David Nissan Cohen, Shauli Ravfogel, Shaltiel Shmidman, Yoav Goldberg
2024 J jnl
GRADE: Quantifying Sample Diversity in Text-to-Image Models.
CoRR
Royi Rassin, Aviv Slobodkin, Shauli Ravfogel, Yanai Elazar, Yoav Goldberg
2024 J jnl
Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces.
CoRR
Yihuai Hong, Lei Yu, Shauli Ravfogel, Haiqin Yang, Mor Geva
2024 A* conf
Language Concept Erasure for Language-invariant Dense Retrieval.
EMNLP
Zhiqi Huang, Puxuan Yu, Shauli Ravfogel, James Allan
2024 J jnl
Language Imbalance Can Boost Cross-lingual Generalisation.
CoRR
Anton Schäfer, Shauli Ravfogel, Thomas Hofmann, Tiago Pimentel, Imanol Schlag
2024 J jnl
MiMiC: Minimally Modified Counterfactuals in the Representation Space.
CoRR
Shashwat Singh, Shauli Ravfogel, Jonathan Herzig, Roee Aharoni, Ryan Cotterell, Ponnurangam Kumaraguru
2024 A* conf
On Affine Homotopy between Language Encoders.
NeurIPS
Robin Chan, Reda Boumasmoud, Anej Svete, Yuxin Ren, Qipeng Guo, Zhijing Jin, Shauli Ravfogel, Mrinmaya Sachan, Bernhard Schölkopf, Mennatallah El-Assady, Ryan Cotterell
2024 J jnl
On Affine Homotopy between Language Encoders.
CoRR
Robin Chan, Reda Boumasmoud, Anej Svete, Yuxin Ren, Qipeng Guo, Zhijing Jin, Shauli Ravfogel, Mrinmaya Sachan, Bernhard Schölkopf, Mennatallah El-Assady, Ryan Cotterell
2024 A* conf
Representation Surgery: Theory and Practice of Affine Steering.
ICML
Shashwat Singh, Shauli Ravfogel, Jonathan Herzig, Roee Aharoni, Ryan Cotterell, Ponnurangam Kumaraguru
2024 J jnl
What Changed? Converting Representational Interventions to Natural Language.
CoRR
Matan Avitan, Ryan Cotterell, Yoav Goldberg, Shauli Ravfogel
2023 J jnl
All Roads Lead to Rome? Exploring the Invariance of Transformers' Representations.
CoRR
Yuxin Ren, Qipeng Guo, Zhijing Jin, Shauli Ravfogel, Mrinmaya Sachan, Bernhard Schölkopf, Ryan Cotterell
2023 — conf
Conformal Nucleus Sampling.
ACL (Findings)
Shauli Ravfogel, Yoav Goldberg, Jacob Goldberger
2023 J jnl
Conformal Nucleus Sampling.
CoRR
Shauli Ravfogel, Yoav Goldberg, Jacob Goldberger
2023 — conf
Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation.
ACL (Findings)
Marius Mosbach, Tiago Pimentel, Shauli Ravfogel, Dietrich Klakow, Yanai Elazar
2023 J jnl
Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation.
CoRR
Marius Mosbach, Tiago Pimentel, Shauli Ravfogel, Dietrich Klakow, Yanai Elazar
2023 — conf
Guiding LLM to Fool Itself: Automatically Manipulating Machine Reading Comprehension Shortcut Triggers.
EMNLP (Findings)
Mosh Levy, Shauli Ravfogel, Yoav Goldberg
2023 J jnl
Guiding LLM to Fool Itself: Automatically Manipulating Machine Reading Comprehension Shortcut Triggers.
CoRR
Mosh Levy, Shauli Ravfogel, Yoav Goldberg
2023 A* conf
LEACE: Perfect linear concept erasure in closed form.
NeurIPS
Nora Belrose, David Schneider-Joseph, Shauli Ravfogel, Ryan Cotterell, Edward Raff, Stella Biderman
2023 J jnl
LEACE: Perfect linear concept erasure in closed form.
CoRR
Nora Belrose, David Schneider-Joseph, Shauli Ravfogel, Ryan Cotterell, Edward Raff, Stella Biderman
2023 — conf
Linear Guardedness and its Implications.
ACL (1)
Shauli Ravfogel, Yoav Goldberg, Ryan Cotterell
2023 A* conf
Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment.
NeurIPS
Royi Rassin, Eran Hirsch, Daniel Glickman, Shauli Ravfogel, Yoav Goldberg, Gal Chechik
2023 J jnl
Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment.
CoRR
Royi Rassin, Eran Hirsch, Daniel Glickman, Shauli Ravfogel, Yoav Goldberg, Gal Chechik
2023 — ed.
Proceedings of the 8th Workshop on Representation Learning for NLP, RepL4NLP@ACL 2023, Toronto, Canada, July 13, 2023.
RepL4NLP@ACL
Burcu Can, Maximilian Mozes, Samuel Cahyawijaya, Naomi Saphra, Nora Kassner, Shauli Ravfogel, Abhilasha Ravichander, Chen Zhao, Isabelle Augenstein, Anna Rogers, Kyunghyun Cho, Edward Grefenstette, Lena Voita
2023 J jnl
Retrieving Texts based on Abstract Descriptions.
CoRR
Shauli Ravfogel, Valentina Pyatkin, Amir David Nissan Cohen, Avshalom Manevich, Yoav Goldberg
2023 A* conf
The Curious Case of Hallucinatory (Un)answerability: Finding Truths in the Hidden States of Over-Confident Large Language Models.
EMNLP
Aviv Slobodkin, Omer Goldman, Avi Caciularu, Ido Dagan, Shauli Ravfogel
2023 J jnl
The Curious Case of Hallucinatory Unanswerablity: Finding Truths in the Hidden States of Over-Confident Large Language Models.
CoRR
Aviv Slobodkin, Omer Goldman, Avi Caciularu, Ido Dagan, Shauli Ravfogel
2023 J jnl
Visual Comparison of Language Model Adaptation.
IEEE Trans. Vis. Comput. Graph.
Rita Sevastjanova, Eren Cakmak, Shauli Ravfogel, Ryan Cotterell, Mennatallah El-Assady
2022 A* conf
Adversarial Concept Erasure in Kernel Space.
EMNLP
Shauli Ravfogel, Francisco Vargas, Yoav Goldberg, Ryan Cotterell
2022 J jnl
Adversarial Concept Erasure in Kernel Space.
CoRR
Shauli Ravfogel, Francisco Vargas, Yoav Goldberg, Ryan Cotterell
2022 — conf
Analyzing Gender Representation in Multilingual Models.
RepL4NLP@ACL
Hila Gonen, Shauli Ravfogel, Yoav Goldberg
2022 J jnl
Analyzing Gender Representation in Multilingual Models.
CoRR
Hila Gonen, Shauli Ravfogel, Yoav Goldberg
2022 — conf
BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models.
ACL (2)
Elad Ben Zaken, Yoav Goldberg, Shauli Ravfogel
2022 — conf
DALLE-2 is Seeing Double: Flaws in Word-to-Concept Mapping in Text2Image Models.
BlackboxNLP@EMNLP
Royi Rassin, Shauli Ravfogel, Yoav Goldberg
2022 J jnl
DALLE-2 is Seeing Double: Flaws in Word-to-Concept Mapping in Text2Image Models.
CoRR
Royi Rassin, Shauli Ravfogel, Yoav Goldberg
2022 A* conf
Linear Adversarial Concept Erasure.
ICML
Shauli Ravfogel, Michael Twiton, Yoav Goldberg, Ryan Cotterell
2022 J jnl
Linear Adversarial Concept Erasure.
CoRR
Shauli Ravfogel, Michael Twiton, Yoav Goldberg, Ryan Cotterell
2022 J jnl
Linear Guardedness and its Implications.
CoRR
Shauli Ravfogel, Yoav Goldberg, Ryan Cotterell
2022 J jnl
Measuring Causal Effects of Data Statistics on Language Model's 'Factual' Predictions.
CoRR
Yanai Elazar, Nora Kassner, Shauli Ravfogel, Amir Feder, Abhilasha Ravichander, Marius Mosbach, Yonatan Belinkov, Hinrich Schütze, Yoav Goldberg
2022 J jnl
Visual Comparison of Language Model Adaptation.
CoRR
Rita Sevastjanova, Eren Cakmak, Shauli Ravfogel, Ryan Cotterell, Mennatallah El-Assady
2021 — conf
Ab Antiquo: Neural Proto-language Reconstruction.
NAACL-HLT
Carlo Meloni, Shauli Ravfogel, Yoav Goldberg
2021 J jnl
Amnesic Probing: Behavioral Explanation With Amnesic Counterfactuals.
Trans. Assoc. Comput. Linguistics
Yanai Elazar, Shauli Ravfogel, Alon Jacovi, Yoav Goldberg
2021 J jnl
BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models.
CoRR
Elad Ben Zaken, Shauli Ravfogel, Yoav Goldberg
2021 — conf
Contrastive Explanations for Model Interpretability.
EMNLP (1)
Alon Jacovi, Swabha Swayamdipta, Shauli Ravfogel, Yanai Elazar, Yejin Choi, Yoav Goldberg
2021 J jnl
Contrastive Explanations for Model Interpretability.
CoRR
Alon Jacovi, Swabha Swayamdipta, Shauli Ravfogel, Yanai Elazar, Yejin Choi, Yoav Goldberg
2021 B conf
Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction.
CoNLL
Shauli Ravfogel, Grusha Prasad, Tal Linzen, Yoav Goldberg
2021 J jnl
Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction.
CoRR
Shauli Ravfogel, Grusha Prasad, Tal Linzen, Yoav Goldberg
2021 J jnl
Erratum: Measuring and Improving Consistency in Pretrained Language Models.
Trans. Assoc. Comput. Linguistics
Yanai Elazar, Nora Kassner, Shauli Ravfogel, Abhilasha Ravichander, Eduard H. Hovy, Hinrich Schütze, Yoav Goldberg
2021 J jnl
Measuring and Improving Consistency in Pretrained Language Models.
CoRR
Yanai Elazar, Nora Kassner, Shauli Ravfogel, Abhilasha Ravichander, Eduard H. Hovy, Hinrich Schütze, Yoav Goldberg
2021 J jnl
Measuring and Improving Consistency in Pretrained Language Models.
Trans. Assoc. Comput. Linguistics
Yanai Elazar, Nora Kassner, Shauli Ravfogel, Abhilasha Ravichander, Eduard H. Hovy, Hinrich Schütze, Yoav Goldberg
2021 — conf
Neural Extractive Search.
ACL (demo)
Shauli Ravfogel, Hillel Taub-Tabib, Yoav Goldberg
2021 J jnl
Neural Extractive Search.
CoRR
Shauli Ravfogel, Hillel Taub-Tabib, Yoav Goldberg
2020 — conf
It's not Greek to mBERT: Inducing Word-Level Translations from Multilingual BERT.
BlackboxNLP@EMNLP
Hila Gonen, Shauli Ravfogel, Yanai Elazar, Yoav Goldberg
2020 J jnl
It's not Greek to mBERT: Inducing Word-Level Translations from Multilingual BERT.
CoRR
Hila Gonen, Shauli Ravfogel, Yanai Elazar, Yoav Goldberg
2020 A* conf
Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection.
ACL
Shauli Ravfogel, Yanai Elazar, Hila Gonen, Michael Twiton, Yoav Goldberg
2020 J jnl
Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection.
CoRR
Shauli Ravfogel, Yanai Elazar, Hila Gonen, Michael Twiton, Yoav Goldberg
2020 — conf
The Extraordinary Failure of Complement Coercion Crowdsourcing.
Insights
Yanai Elazar, Victoria Basmova, Shauli Ravfogel, Yoav Goldberg, Reut Tsarfaty
2020 J jnl
The Extraordinary Failure of Complement Coercion Crowdsourcing.
CoRR
Yanai Elazar, Victoria Basmova, Shauli Ravfogel, Yoav Goldberg, Reut Tsarfaty
2020 — conf
Unsupervised Distillation of Syntactic Information from Contextualized Word Representations.
BlackboxNLP@EMNLP
Shauli Ravfogel, Yanai Elazar, Jacob Goldberger, Yoav Goldberg
2020 J jnl
Unsupervised Distillation of Syntactic Information from Contextualized Word Representations.
CoRR
Shauli Ravfogel, Yanai Elazar, Jacob Goldberger, Yoav Goldberg
2020 J jnl
When Bert Forgets How To POS: Amnesic Probing of Linguistic Properties and MLM Predictions.
CoRR
Yanai Elazar, Shauli Ravfogel, Alon Jacovi, Yoav Goldberg
2019 J jnl
Ab Antiquo: Proto-language Reconstruction with RNNs.
CoRR
Carlo Meloni, Shauli Ravfogel, Yoav Goldberg
2019 — conf
Studying the Inductive Biases of RNNs with Synthetic Variations of Natural Languages.
NAACL-HLT (1)
Shauli Ravfogel, Yoav Goldberg, Tal Linzen
2019 J jnl
Studying the Inductive Biases of RNNs with Synthetic Variations of Natural Languages.
CoRR
Shauli Ravfogel, Yoav Goldberg, Tal Linzen
2018 — conf
Can LSTM Learn to Capture Agreement? The Case of Basque.
BlackboxNLP@EMNLP
Shauli Ravfogel, Yoav Goldberg, Francis M. Tyers
2018 J jnl
Can LSTM Learn to Capture Agreement? The Case of Basque.
CoRR
Shauli Ravfogel, Francis M. Tyers, Yoav Goldberg