Author

Dana Arad

Observed name: Arad, Dana

Institution: Technion – Israel Institute of Technology

Observed institutions: Tel Aviv University, Technion – Israel Institute of Technology

OpenAlex ID: A5023607289

ReFACT: Updating Text-to-Image Models by Editing the Text Encoder

2024 · Dana Arad, Hadas Orgad, et al. · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · 13

Diffusion Lens: Interpreting Text Encoders in Text-to-Image Pipelines

2024 · Michael Toker, Hadas Orgad, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting · 6

LearnShapley: Learning to Predict Rankings of Facts Contribution Based on Query Logs

2022 · Dana Arad, Daniel Deutch, et al. · ACM International Conference on Information and Knowledge Management (CIKM) · 3

Mechanisms of Prompt-Induced Hallucination in Vision–Language Models

2026 · William Rudman, Michal Golovanevsky, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting · 1

PDF

MIB: A Mechanistic Interpretability Benchmark

2025 · Mueller, Aaron, Geiger, Atticus, et al. · UvA-DARE (University of Amsterdam) · 1

CRISP: Persistent Concept Unlearning via Sparse Autoencoders

2026 · Association for Computational Linguistics 2026, Arad, Dana, et al. · Underline Science Inc.

Mechanisms of Prompt-Induced Hallucination in Vision–Language Models

2026 · Association for Computational Linguistics 2026, Arad, Dana, et al. · Underline Science Inc.

Mechanisms of Prompt-Induced Hallucination in Vision-Language Models

2026 · Rudman, William, Golovanevsky, Michal, et al. · arXiv (Cornell University)

PDF

CRISP: Persistent Concept Unlearning via Sparse Autoencoders

2026 · Tomer Ashuach, Dana Arad, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting

Front Matter

2026 · Dana Arad, Yonatan Belinkov, et al. · BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP)

PDF

Can LLMs Detect Ambiguous Plural Reference?: An Analysis of Split-Antecedent and Mereological Reference

2025 · Dang, Anh, Nouwen, Rick, et al. · Utrecht University Repository (Utrecht University)

BlackboxNLP-2025 MIB Shared Task: Improving Circuit Faithfulness via Better Edge Selection

2025 · Yaniv Nikankin, Dana Arad, et al. · BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP)

PDF

ReFACT: Updating Text-to-Image Models by Editing the Text Encoder

2023 · Arad, Dana, Orgad, Hadas, et al. · arXiv (Cornell University)

PDF

Works count: 17

Citation count: 24

H-index: 3

I10-index: 1