publications

2025

1. 

   SAEs Are Good for Steering - If You Select the Right Features

   Dana Arad, Aaron Mueller, and Yonatan Belinkov

   arXiv, 2025

   arXiv Bib

   @article{DBLP:journals/corr/abs-2505-20063,
     author = {Arad, Dana and Mueller, Aaron and Belinkov, Yonatan},
     title = {SAEs Are Good for Steering - If You Select the Right Features},
     journal = {arXiv},
     volume = {abs/2505.20063},
     year = {2025},
     url = {https://doi.org/10.48550/arXiv.2505.20063},
     eprinttype = {arXiv},
     eprint = {2505.20063},
     timestamp = {Fri, 27 Jun 2025 21:43:42 +0200},
     biburl = {https://dblp.org/rec/journals/corr/abs-2505-20063.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org},
   }

2. 

   Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs

   Yaniv Nikankin, Dana Arad, Yossi Gandelsman, and 1 more author

   arXiv, 2025

   arXiv Bib Website

   @article{DBLP:journals/corr/abs-2506-09047,
     author = {Nikankin, Yaniv and Arad, Dana and Gandelsman, Yossi and Belinkov, Yonatan},
     title = {Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms
                       in VLMs},
     journal = {arXiv},
     volume = {abs/2506.09047},
     year = {2025},
     url = {https://doi.org/10.48550/arXiv.2506.09047},
     eprinttype = {arXiv},
     eprint = {2506.09047},
     timestamp = {Tue, 08 Jul 2025 20:40:20 +0200},
     biburl = {https://dblp.org/rec/journals/corr/abs-2506-09047.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org},
   }

3. ICML

   

   MIB: A Mechanistic Interpretability Benchmark

   Aaron Mueller, Atticus Geiger, Sarah Wiegreffe, and 20 more authors

   ICML, 2025

   arXiv Bib

   @article{DBLP:journals/corr/abs-2504-13151,
     author = {Mueller, Aaron and Geiger, Atticus and Wiegreffe, Sarah and Arad, Dana and Arcuschin, Iv{\'{a}}n and Belfki, Adam and Chan, Yik Siu and Fiotto{-}Kaufman, Jaden and Haklay, Tal and Hanna, Michael and Huang, Jing and Gupta, Rohan and Nikankin, Yaniv and Orgad, Hadas and Prakash, Nikhil and Reusch, Anja and Sankaranarayanan, Aruna and Shao, Shun and Stolfo, Alessandro and Tutek, Martin and Zur, Amir and Bau, David and Belinkov, Yonatan},
     title = {{MIB:} {A} Mechanistic Interpretability Benchmark},
     journal = {ICML},
     volume = {abs/2504.13151},
     year = {2025},
     url = {https://doi.org/10.48550/arXiv.2504.13151},
     eprinttype = {arXiv},
     eprint = {2504.13151},
     timestamp = {Thu, 22 May 2025 21:00:35 +0200},
     biburl = {https://dblp.org/rec/journals/corr/abs-2504-13151.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org},
   }

2024

1. ACL

   

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

   Michael Toker, Hadas Orgad, Mor Ventura, and 2 more authors

   In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2024, Bangkok, Thailand, August 11-16, 2024, 2024

   arXiv Bib Website

   @inproceedings{DBLP:conf/acl/TokerOVAB24,
     author = {Toker, Michael and Orgad, Hadas and Ventura, Mor and Arad, Dana and Belinkov, Yonatan},
     editor = {Ku, Lun{-}Wei and Martins, Andre and Srikumar, Vivek},
     title = {Diffusion Lens: Interpreting Text Encoders in Text-to-Image Pipelines},
     booktitle = {Proceedings of the 62nd Annual Meeting of the Association for Computational
                       Linguistics (Volume 1: Long Papers), {ACL} 2024, Bangkok, Thailand,
                       August 11-16, 2024},
     pages = {9713--9728},
     publisher = {Association for Computational Linguistics},
     year = {2024},
     url = {https://doi.org/10.18653/v1/2024.acl-long.524},
     timestamp = {Tue, 24 Sep 2024 10:55:49 +0200},
     biburl = {https://dblp.org/rec/conf/acl/TokerOVAB24.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org},
   }

2. NAACL

   

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

   Dana Arad, Hadas Orgad, and Yonatan Belinkov

   In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), NAACL 2024, Mexico City, Mexico, June 16-21, 2024, 2024

   arXiv Bib Website

   @inproceedings{DBLP:conf/naacl/AradOB24,
     author = {Arad, Dana and Orgad, Hadas and Belinkov, Yonatan},
     editor = {Duh, Kevin and G{\'{o}}mez{-}Adorno, Helena and Bethard, Steven},
     title = {ReFACT: Updating Text-to-Image Models by Editing the Text Encoder},
     booktitle = {Proceedings of the 2024 Conference of the North American Chapter of
                       the Association for Computational Linguistics: Human Language Technologies
                       (Volume 1: Long Papers), {NAACL} 2024, Mexico City, Mexico, June 16-21,
                       2024},
     pages = {2537--2558},
     publisher = {Association for Computational Linguistics},
     year = {2024},
     url = {https://doi.org/10.18653/v1/2024.naacl-long.140},
     timestamp = {Thu, 29 Aug 2024 17:13:57 +0200},
     biburl = {https://dblp.org/rec/conf/naacl/AradOB24.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org},
   }

3. EDBT

   Predicting Fact Contributions from Query Logs with Machine Learning

   Dana Arad, Daniel Deutch, and Nave Frost

   In Proceedings 27th International Conference on Extending Database Technology, EDBT 2024, Paestum, Italy, March 25 - March 28, 2024

   Bib

   @inproceedings{DBLP:conf/edbt/AradDF24,
     author = {Arad, Dana and Deutch, Daniel and Frost, Nave},
     editor = {Tanca, Letizia and Luo, Qiong and Polese, Giuseppe and Caruccio, Loredana and Oriol, Xavier and Firmani, Donatella},
     title = {Predicting Fact Contributions from Query Logs with Machine Learning},
     booktitle = {Proceedings 27th International Conference on Extending Database Technology,
                       {EDBT} 2024, Paestum, Italy, March 25 - March 28},
     pages = {704--716},
     publisher = {OpenProceedings.org},
     year = {2024},
     url = {https://doi.org/10.48786/edbt.2024.60},
     timestamp = {Mon, 10 Mar 2025 16:32:46 +0100},
     biburl = {https://dblp.org/rec/conf/edbt/AradDF24.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org},
   }

2022

1. CIKM

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

   Dana Arad, Daniel Deutch, and Nave Frost

   In Proceedings of the 31st ACM International Conference on Information & Knowledge Management, Atlanta, GA, USA, October 17-21, 2022, 2022

   Bib

   @inproceedings{DBLP:conf/cikm/AradDF22,
     author = {Arad, Dana and Deutch, Daniel and Frost, Nave},
     editor = {Hasan, Mohammad Al and Xiong, Li},
     title = {LearnShapley: Learning to Predict Rankings of Facts Contribution Based
                       on Query Logs},
     booktitle = {Proceedings of the 31st {ACM} International Conference on Information
                       {\&} Knowledge Management, Atlanta, GA, USA, October 17-21, 2022},
     pages = {4788--4792},
     publisher = {{ACM}},
     year = {2022},
     url = {https://doi.org/10.1145/3511808.3557204},
     timestamp = {Wed, 19 Oct 2022 17:09:02 +0200},
     biburl = {https://dblp.org/rec/conf/cikm/AradDF22.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org},
   }