← Authors

Yonatan Belinkov

97 papers · 2013–2025 · 14 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (14) 🐣 Hot Topic Early Bird πŸ—ΊοΈ Taxonomy Completionist (118) 🌈 Renaissance Researcher (9) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (7) πŸƒ Academic Marathon (12) 🌟 Keyword Trendsetter Combo (5) 🏠 Conference Loyalist (24) πŸ‘₯ Mega-Team (61) πŸ† Grand Slam 🀝 Dynamic Duo (14) 🌱 Topic Pioneer πŸ”¬ Deep Specialist (28) 🧬 Topic Evolution πŸ† Keyword Champion ❓ The Questioner (4) πŸ“ˆ Trend Setter πŸ—ƒοΈ Keyword Collector (328) πŸ”₯ Unstoppable (11) πŸ’Ž Century Club (97) ⚑ Prolific Year (7) πŸš€ Conference Pioneer

Conferences

ACL (24) EMNLP (17) ICLR (16) NAACL (13) NIPS (7) AAAI (6) EACL (3) IJCNLP (3) INTERSPEECH (2) SEMEVAL (2) COLING (1) ICCV (1) ICML (1) WACV (1)

Top co-authors

Hassan Sajjad (14) James Glass (14) Nadir Durrani (13) Fahim Dalvi (11) Hadas Orgad (11) Aaron Mueller (8) David Bau (8) Stuart Shieber (6) Dana Arad (6) Boaz Carmeli (5)

Research topics

Reasoning (1)

Keywords

representation learning (18) language model (13) neural network (9) neural machine translation (9) attention mechanism (9) natural language inference (8) bias mitigation (5) model editing (4) out-of-distribution generalization (4) causal mediation analysis (4) emergent communication (4) neuron analysis (4) large language model (4) model interpretability (4) diffusion model (4) domain adaptation (3) transfer learning (3) domain generalization (3) mechanistic interpretability (3) unsupervised learning (2)

Papers

Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions ICLR 2025
MIB: A Mechanistic Interpretability Benchmark ICML 2025
Position-aware Automatic Circuit Discovery ACL 2025
Findings of the BlackboxNLP 2025 Shared Task: Localizing Circuits and Causal Variables in Language Models EMNLP 2025
BlackboxNLP-2025 MIB Shared Task: Improving Circuit Faithfulness via Better Edge Selection EMNLP 2025
Trust Me, I’m Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer EMNLP 2025
Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models EMNLP 2025
SAEs Are Good for Steering – If You Select the Right Features EMNLP 2025
Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps EMNLP 2025
REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space ACL 2025
DEPTH: Discourse Education through Pre-Training Hierarchically NAACL 2025
Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models NAACL 2025
Unsupervised Translation of Emergent Communication AAAI 2025
Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models ICLR 2025
CtD: Composition through Decomposition in Emergent Communication ICLR 2025
Jamba: Hybrid Transformer-Mamba Language Models ICLR 2025
Arithmetic Without Algorithms: Language Models Solve Math with a Bag of Heuristics ICLR 2025
LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations ICLR 2025
Concept-Best-Matching: Evaluating Compositionality In Emergent Communication ACL 2024
Backward Lens: Projecting Language Model Gradients into the Vocabulary Space EMNLP 2024
A Dataset for Metaphor Detection in Early Medieval Hebrew Poetry EACL 2024
Generating Benchmarks for Factuality Evaluation of Language Models EACL 2024
Confidence Regulation Neurons in Language Models NIPS 2024
ContraSim – Analyzing Neural Representations Based on Contrastive Learning NAACL 2024
ReFACT: Updating Text-to-Image Models by Editing the Text Encoder NAACL 2024
Unified Concept Editing in Diffusion Models WACV 2024
Accelerating the Global Aggregation of Local Explanations AAAI 2024
Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking ICLR 2024
Linearity of Relation Decoding in Transformer Language Models ICLR 2024
Fast Forwarding Low-Rank Training EMNLP 2024
Leveraging Prototypical Representations for Mitigating Social Bias without Demographic Information NAACL 2024
Semantics and Spatiality of Emergent Communication NIPS 2024
Diffusion Lens: Interpreting Text Encoders in Text-to-Image Pipelines ACL 2024
Learning from Others: Similarity-based Regularization for Mitigating Dataset Bias. ACL 2024
When Language Models Fall in Love: Animacy Processing in Transformer Language Models EMNLP 2023
Emergent Quantized Communication AAAI 2023
What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary ACL 2023
Parallel Context Windows for Large Language Models ACL 2023
BLIND: Bias Removal With No Demographics ACL 2023
Shielded Representations: Protecting Sensitive Attributes Through Iterative Gradient-Based Projection ACL 2023
A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis EMNLP 2023
VISIT: Visualizing and Interpreting the Semantic Information Flow of Transformers EMNLP 2023
Editing Implicit Assumptions in Text-to-Image Diffusion Models ICCV 2023
Multiple sequence alignment as a sequence-to-sequence learning problem ICLR 2023
Mass-Editing Memory in a Transformer ICLR 2023
Locating and Editing Factual Associations in GPT NIPS 2022
Measures of Information Reflect Memorization Patterns NIPS 2022
A Generative Approach for Mitigating Structural Biases in Natural Language Inference NAACL 2022
Choose Your Lenses: Flaws in Gender Bias Evaluation NAACL 2022
Supervising Model Attention with Human Explanations for Robust Natural Language Inference AAAI 2022
A Multilingual Perspective Towards the Evaluation of Attribution Methods in Natural Language Inference EMNLP 2022
IDANI: Inference-time Domain Adaptation via Neuron-level Interventions NAACL 2022
How Gender Debiasing Affects Internal Model Representations, and Why It Matters NAACL 2022
On the Pitfalls of Analyzing Individual Neurons in Language Models ICLR 2022
Learning from others' mistakes: Avoiding dataset biases without modeling them ICLR 2021
Variational Information Bottleneck for Effective Low-Resource Fine-Tuning ICLR 2021
Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance? EACL 2021
Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models ACL 2021
Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models IJCNLP 2021
Debiasing Methods in Natural Language Understanding Make Bias More Accessible EMNLP 2021
IRMβ€”when it works and when it doesn't: A test case of natural language inference NIPS 2021
Analyzing Individual Neurons in Pre-trained Language Models EMNLP 2020
Interpretability and Analysis in Neural NLP ACL 2020
End-to-End Bias Mitigation by Modelling Biases in Corpora ACL 2020
The Sensitivity of Language Models and Humans to Winograd Schema Perturbations ACL 2020
Similarity Analysis of Contextual Word Representation Models ACL 2020
Probing Neural Dialog Models for Conversational Understanding ACL 2020
A Constructive Prediction of the Generalization Error Across Scales ICLR 2020
Investigating Gender Bias in Language Models Using Causal Mediation Analysis NIPS 2020
Findings of the WMT 2020 Shared Task on Machine Translation Robustness EMNLP 2020
Analyzing Redundancy in Pretrained Transformer Models EMNLP 2020
What Is One Grain of Sand in the Desert? Analyzing Individual Neurons in Deep NLP Models AAAI 2019
Findings of the First Shared Task on Machine Translation Robustness ACL 2019
Identifying and Controlling Important Neurons in Neural Machine Translation ICLR 2019
Analyzing the Structure of Attention in a Transformer Language Model ACL 2019
Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP ACL 2019
Improving Neural Language Models by Segmenting, Attending, and Predicting the Future ACL 2019
Don’t Take the Premise for Granted: Mitigating Artifacts in Natural Language Inference ACL 2019
LSTM Networks Can Perform Dynamic Counting ACL 2019
Analyzing Phonetic and Graphemic Representations in End-to-End Automatic Speech Recognition INTERSPEECH 2019
Adversarial Regularization for Visual Question Answering: Strengths, Shortcomings, and Side Effects NAACL 2019
Linguistic Knowledge and Transferability of Contextual Representations NAACL 2019
One Size Does Not Fit All: Comparing NMT Representations of Different Granularities NAACL 2019
NeuroX: A Toolkit for Analyzing Individual Neurons in Neural Networks AAAI 2019
Synthetic and Natural Noise Both Break Neural Machine Translation ICLR 2018
On the Evaluation of Semantic Phenomena in Neural Machine Translation Using Natural Language Inference NAACL 2018
What do Neural Machine Translation Models Learn about Morphology? ACL 2017
Analyzing Hidden Representations in End-to-End Automatic Speech Recognition Systems NIPS 2017
Challenging Language-Dependent Segmentation for Arabic: An Application to Machine Translation and Part-of-Speech Tagging ACL 2017
QMDIS: QCRI-MIT Advanced Dialect Identification System INTERSPEECH 2017
Understanding and Improving Morphological Learning in the Neural Machine Translation Decoder IJCNLP 2017
Evaluating Layers of Representation in Neural Machine Translation on Part-of-Speech and Semantic Tagging Tasks IJCNLP 2017
Neural Attention for Learning to Rank Questions in Community Question Answering COLING 2016
SLS at SemEval-2016 Task 3: Neural-based Approaches for Ranking in Community Question Answering SEMEVAL 2016
Arabic Diacritization with Recurrent Neural Networks EMNLP 2015
VectorSLU: A Continuous Word Vector Approach to Answer Selection in Community Question Answering Systems SEMEVAL 2015
Translating Dialectal Arabic to English ACL 2013