@inproceedings{nikankin-etal-2025-blackboxnlp,
    title = "{B}lackbox{NLP}-2025 {MIB} Shared Task: Improving Circuit Faithfulness via Better Edge Selection",
    author = "Nikankin, Yaniv  and
      Arad, Dana  and
      Itzhak, Itay  and
      Reusch, Anja  and
      Simhi, Adi  and
      Kesten, Gal  and
      Belinkov, Yonatan",
    editor = "Belinkov, Yonatan  and
      Mueller, Aaron  and
      Kim, Najoung  and
      Mohebbi, Hosein  and
      Chen, Hanjie  and
      Arad, Dana  and
      Sarti, Gabriele",
    booktitle = "Proceedings of the 8th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.blackboxnlp-1.29/",
    pages = "521--527",
    ISBN = "979-8-89176-346-3",
    abstract = "One of the main challenges in mechanistic interpretability is circuit discovery {--} determining which parts of a model perform a given task. We build on the Mechanistic Interpretability Benchmark (MIB) and propose three key improvements to circuit discovery. First, we use bootstrapping to identify edges with consistent attribution scores. Second, we introduce a simple ratio-based selection strategy to prioritize strong positive-scoring edges, balancing performance and faithfulness. Third, we replace the standard greedy selection with an integer linear programming formulation. Our methods yield more faithful circuits and outperform prior approaches across multiple MIB tasks and models."
}