PPaperPicks

Yonatan Belinkov

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

DBLP profile ↗ORCID search ↗

Venues

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

Frequent coauthors

Tomer Ashuach
DBLP profile ↗ORCID search ↗
×3
Adir Rahamim
DBLP profile ↗ORCID search ↗
×3
Yaniv Nikankin
DBLP profile ↗ORCID search ↗
×2
Boaz Carmeli
DBLP profile ↗ORCID search ↗
×2
Michael Toker
DBLP profile ↗ORCID search ↗
×2
Dana Arad
DBLP profile ↗ORCID search ↗
×2
Guy Kaplan
DBLP profile ↗ORCID search ↗
×1
William Rudman
DBLP profile ↗ORCID search ↗
×1
Sarah Wiegreffe
DBLP profile ↗ORCID search ↗
×1
Zeping Yu
DBLP profile ↗ORCID search ↗
×1
Hadas Orgad
DBLP profile ↗ORCID search ↗
×1
Aaron Mueller
DBLP profile ↗ORCID search ↗
×1

Papers

  1. CRISP: Persistent Concept Unlearning via Sparse Autoencoders
    ACL 2026 ·
    Tomer Ashuach
    DBLP profile ↗ORCID search ↗
  2. Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models
    ACL 2026 ·
    Guy Kaplan
    DBLP profile ↗ORCID search ↗
  3. Masked by Consensus: Disentangling Privileged Knowledge in LLM Correctness
    ACL 2026 ·
    Tomer Ashuach
    DBLP profile ↗ORCID search ↗
  4. Mechanisms of Prompt-Induced Hallucination in Vision-Language Models
    ACL 2026 ·
    William Rudman
    DBLP profile ↗ORCID search ↗
  5. Will it Merge? On The Causes of Model Mergeability
    ACL 2026 ·
    Adir Rahamim
    DBLP profile ↗ORCID search ↗
  6. Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions
    ICLR 2025 ·
    Sarah Wiegreffe
    DBLP profile ↗ORCID search ↗
  7. Arithmetic Without Algorithms: Language Models Solve Math with a Bag of Heuristics
    ICLR 2025 ·
    Yaniv Nikankin
    DBLP profile ↗ORCID search ↗
  8. Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models
    EMNLP 2025 ·
    Zeping Yu
    DBLP profile ↗ORCID search ↗
  9. CtD: Composition through Decomposition in Emergent Communication
    ICLR 2025 ·
    Boaz Carmeli
    DBLP profile ↗ORCID search ↗
  10. LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations
    ICLR 2025 ·
    Hadas Orgad
    DBLP profile ↗ORCID search ↗
  11. MIB: A Mechanistic Interpretability Benchmark
    ICML 2025 ·
    Aaron Mueller
    DBLP profile ↗ORCID search ↗
  12. Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps
    EMNLP 2025 ·
    Martin Tutek
    DBLP profile ↗ORCID search ↗
  13. Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models
    NAACL 2025 ·
    Michael Toker
    DBLP profile ↗ORCID search ↗
  14. Position-aware Automatic Circuit Discovery
    ACL 2025 ·
    Tal Haklay
    DBLP profile ↗ORCID search ↗
  15. REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space
    ACL 2025 ·
    Tomer Ashuach
    DBLP profile ↗ORCID search ↗
  16. Reverse-Engineering the Retrieval Process in GenIR Models
    SIGIR 2025 ·
    Anja Reusch
    DBLP profile ↗ORCID search ↗
  17. SAEs Are Good for Steering - If You Select the Right Features
    EMNLP 2025 ·
    Dana Arad
    DBLP profile ↗ORCID search ↗
  18. Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs
    NeurIPS 2025 ·
    Yaniv Nikankin
    DBLP profile ↗ORCID search ↗
  19. Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
    ICLR 2025 ·
    Samuel Marks
    DBLP profile ↗ORCID search ↗
  20. Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer
    EMNLP 2025 ·
    Adi Simhi
    DBLP profile ↗ORCID search ↗
  21. Unsupervised Translation of Emergent Communication
    AAAI 2025 ·
    Ido Levy
    DBLP profile ↗ORCID search ↗
  22. Accelerating the Global Aggregation of Local Explanations
    AAAI 2024 ·
    Alon Mor
    DBLP profile ↗ORCID search ↗
  23. Backward Lens: Projecting Language Model Gradients into the Vocabulary Space
    EMNLP 2024 ·
    Shahar Katz
    DBLP profile ↗ORCID search ↗
  24. Concept-Best-Matching: Evaluating Compositionality In Emergent Communication
    ACL 2024 ·
    Boaz Carmeli
    DBLP profile ↗ORCID search ↗
  25. Confidence Regulation Neurons in Language Models
    NeurIPS 2024 ·
    Alessandro Stolfo
    DBLP profile ↗ORCID search ↗
  26. ContraSim - Analyzing Neural Representations Based on Contrastive Learning
    NAACL 2024 ·
    Adir Rahamim
    DBLP profile ↗ORCID search ↗
  27. Diffusion Lens: Interpreting Text Encoders in Text-to-Image Pipelines
    ACL 2024 ·
    Michael Toker
    DBLP profile ↗ORCID search ↗
  28. Fast Forwarding Low-Rank Training
    EMNLP 2024 ·
    Adir Rahamim
    DBLP profile ↗ORCID search ↗
  29. Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking
    ICLR 2024 ·
    Nikhil Prakash
    DBLP profile ↗ORCID search ↗
  30. Leveraging Prototypical Representations for Mitigating Social Bias without Demographic Information
    NAACL 2024 ·
    Shadi Iskander
    DBLP profile ↗ORCID search ↗
  31. Linearity of Relation Decoding in Transformer Language Models
    ICLR 2024 ·
    Evan Hernandez
    DBLP profile ↗ORCID search ↗
  32. ReFACT: Updating Text-to-Image Models by Editing the Text Encoder
    NAACL 2024 ·
    Dana Arad
    DBLP profile ↗ORCID search ↗
  33. Semantics and Spatiality of Emergent Communication
    NeurIPS 2024 ·
    Rotem Ben Zion
    DBLP profile ↗ORCID search ↗