Yonatan Belinkov

33 papers at tracked venues · 23 at CORE A* · active 2024–2026

DBLP profile ↗ORCID search ↗

Venues

ACL ×9 ICLR ×7 EMNLP ×6 NAACL ×4 NeurIPS ×3 AAAI ×2 ICML ×1 SIGIR ×1

Frequent coauthors

Dana Arad

×7

Aaron Mueller

×6

Hadas Orgad

×6

Boaz Carmeli

×5

David Bau

×5

Martin Tutek

×4

Michael Toker

×4

Tal Haklay

×4

Tomer Ashuach

×3

Adir Rahamim

×3

Yaniv Nikankin

×3

Anja Reusch

×3

Papers

CRISP: Persistent Concept Unlearning via Sparse Autoencoders
ACL 2026 ·
Tomer Ashuach
,
Dana Arad
,
Aaron Mueller
,
Martin Tutek
, Yonatan Belinkov
Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models
ACL 2026 ·
Guy Kaplan
,
Michael Toker
,
Yuval Reif
, Yonatan Belinkov,
Roy Schwartz
Masked by Consensus: Disentangling Privileged Knowledge in LLM Correctness
ACL 2026 ·
Tomer Ashuach
,
Shai Gretz
,
Yoav Katz
, Yonatan Belinkov,
Liat Ein-Dor
Mechanisms of Prompt-Induced Hallucination in Vision-Language Models
ACL 2026 ·
William Rudman
,
Michal Golovanevsky
,
Dana Arad
, Yonatan Belinkov,
Carsten Eickhoff
,
Ritambhara Singh
,
Kyle Mahowald
Will it Merge? On The Causes of Model Mergeability
ACL 2026 ·
Adir Rahamim
,
Asaf Yehudai
,
Boaz Carmeli
,
Leshem Choshen
,
Yosi Mass
, Yonatan Belinkov
Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions
ICLR 2025 ·
Sarah Wiegreffe
,
Oyvind Tafjord
, Yonatan Belinkov,
Hannaneh Hajishirzi
,
Ashish Sabharwal
Arithmetic Without Algorithms: Language Models Solve Math with a Bag of Heuristics
ICLR 2025 ·
Yaniv Nikankin
,
Anja Reusch
,
Aaron Mueller
, Yonatan Belinkov
Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models
EMNLP 2025 ·
Zeping Yu
, Yonatan Belinkov,
Sophia Ananiadou
CtD: Composition through Decomposition in Emergent Communication
ICLR 2025 ·
Boaz Carmeli
,
Ron Meir
, Yonatan Belinkov
LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations
ICLR 2025 ·
Hadas Orgad
,
Michael Toker
,
Zorik Gekhman
,
Roi Reichart
,
Idan Szpektor
,
Hadas Kotek
, Yonatan Belinkov
MIB: A Mechanistic Interpretability Benchmark
ICML 2025 ·
Aaron Mueller
,
Atticus Geiger
,
Sarah Wiegreffe
,
Dana Arad
,
Iván Arcuschin
,
Adam Belfki
,
Yik Siu Chan
,
Jaden Fried Fiotto-Kaufman
,
Tal Haklay
,
Michael Hanna
,
Jing Huang
,
Rohan Gupta
,
Yaniv Nikankin
,
Hadas Orgad
,
Nikhil Prakash
,
Anja Reusch
,
Aruna Sankaranarayanan
,
Shun Shao
,
Alessandro Stolfo
,
Martin Tutek
,
Amir Zur
,
David Bau
, Yonatan Belinkov
Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps
EMNLP 2025 ·
Martin Tutek
,
Fateme Hashemi Chaleshtori
,
Ana Marasovic
, Yonatan Belinkov
Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models
NAACL 2025 ·
Michael Toker
,
Ido Galil
,
Hadas Orgad
,
Rinon Gal
,
Yoad Tewel
,
Gal Chechik
, Yonatan Belinkov
Position-aware Automatic Circuit Discovery
ACL 2025 ·
Tal Haklay
,
Hadas Orgad
,
David Bau
,
Aaron Mueller
, Yonatan Belinkov
REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space
ACL 2025 ·
Tomer Ashuach
,
Martin Tutek
, Yonatan Belinkov
Reverse-Engineering the Retrieval Process in GenIR Models
SIGIR 2025 ·
Anja Reusch
, Yonatan Belinkov
SAEs Are Good for Steering - If You Select the Right Features
EMNLP 2025 ·
Dana Arad
,
Aaron Mueller
, Yonatan Belinkov
Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs
NeurIPS 2025 ·
Yaniv Nikankin
,
Dana Arad
,
Yossi Gandelsman
, Yonatan Belinkov
Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
ICLR 2025 ·
Samuel Marks
,
Can Rager
,
Eric J. Michaud
, Yonatan Belinkov,
David Bau
,
Aaron Mueller
Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer
EMNLP 2025 ·
Adi Simhi
,
Itay Itzhak
,
Fazl Barez
,
Gabriel Stanovsky
, Yonatan Belinkov
Unsupervised Translation of Emergent Communication
AAAI 2025 ·
Ido Levy
,
Orr Paradise
,
Boaz Carmeli
,
Ron Meir
,
Shafi Goldwasser
, Yonatan Belinkov
Accelerating the Global Aggregation of Local Explanations
AAAI 2024 ·
Alon Mor
, Yonatan Belinkov,
Benny Kimelfeld
Backward Lens: Projecting Language Model Gradients into the Vocabulary Space
EMNLP 2024 ·
Shahar Katz
, Yonatan Belinkov,
Mor Geva
,
Lior Wolf
Concept-Best-Matching: Evaluating Compositionality In Emergent Communication
ACL 2024 ·
Boaz Carmeli
, Yonatan Belinkov,
Ron Meir
Confidence Regulation Neurons in Language Models
NeurIPS 2024 ·
Alessandro Stolfo
,
Ben Wu
,
Wes Gurnee
, Yonatan Belinkov,
Xingyi Song
,
Mrinmaya Sachan
,
Neel Nanda
ContraSim - Analyzing Neural Representations Based on Contrastive Learning
NAACL 2024 ·
Adir Rahamim
, Yonatan Belinkov
Diffusion Lens: Interpreting Text Encoders in Text-to-Image Pipelines
ACL 2024 ·
Michael Toker
,
Hadas Orgad
,
Mor Ventura
,
Dana Arad
, Yonatan Belinkov
Fast Forwarding Low-Rank Training
EMNLP 2024 ·
Adir Rahamim
,
Naomi Saphra
,
Sara Kangaslahti
, Yonatan Belinkov
Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking
ICLR 2024 ·
Nikhil Prakash
,
Tamar Rott Shaham
,
Tal Haklay
, Yonatan Belinkov,
David Bau
Leveraging Prototypical Representations for Mitigating Social Bias without Demographic Information
NAACL 2024 ·
Shadi Iskander
,
Kira Radinsky
, Yonatan Belinkov
Linearity of Relation Decoding in Transformer Language Models
ICLR 2024 ·
Evan Hernandez
,
Arnab Sen Sharma
,
Tal Haklay
,
Kevin Meng
,
Martin Wattenberg
,
Jacob Andreas
, Yonatan Belinkov,
David Bau
ReFACT: Updating Text-to-Image Models by Editing the Text Encoder
NAACL 2024 ·
Dana Arad
,
Hadas Orgad
, Yonatan Belinkov
Semantics and Spatiality of Emergent Communication
NeurIPS 2024 ·
Rotem Ben Zion
,
Boaz Carmeli
,
Orr Paradise
, Yonatan Belinkov