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

Yaniv Nikankin | Dana Arad | Itay Itzhak | Anja Reusch | Adi Simhi | Gal Kesten | Yonatan Belinkov |

Proceedings of the 8th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP BlackboxNLP WS

Yonatan Belinkov | Aaron Mueller | Najoung Kim | Hosein Mohebbi | Hanjie Chen | Dana Arad | Gabriele Sarti |

SAEs Are Good for Steering – If You Select the Right Features EMNLP

Dana Arad | Aaron Mueller | Yonatan Belinkov |

Findings of the BlackboxNLP 2025 Shared Task: Localizing Circuits and Causal Variables in Language Models BlackboxNLP WS

Dana Arad | Yonatan Belinkov | Hanjie Chen | Najoung Kim | Hosein Mohebbi | Aaron Mueller | Gabriele Sarti | Martin Tutek |