@proceedings{blackboxnlp-2026-1,
    title = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.0/",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{yang-2026-import,
    title = "import pandas as np: the numpy strikes back",
    author = "Yang, Haotian",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.1/",
    pages = "1--14",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{macocco-etal-2026-effectiveness,
    title = "On The Effectiveness-Fluency Trade-Off In {LLM} Conditioning: A Systematic Study",
    author = "Macocco, Iuri  and
      Rodriguez, Pau  and
      Blaas, Arno  and
      Zappella, Luca  and
      Baroni, Marco  and
      Suau, Xavier",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.2/",
    pages = "15--33",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{floro-benedetto-2026-cultural,
    title = "Cultural Binding Heads in Language Models",
    author = "Floro, Avrile  and
      Benedetto, Luca",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.3/",
    pages = "34--48",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{ferner-wegenkittl-2026-lost,
    title = "Lost in Specialization: Embedding Geometry and Retrieval Quality Across Specialized Corpora",
    author = "Ferner, Cornelia  and
      Wegenkittl, Stefan",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.4/",
    pages = "49--57",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{regneri-etal-2026-compact,
    title = "Compact Language, Complex Model Shifts: How and Where Ambiguity and Underspecification Affect {LLM}s",
    author = {Regneri, Michaela  and
      Scheller, Nina  and
      Laue, S{\"o}ren},
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.5/",
    pages = "58--75",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{elaasar-lopes-2026-much,
    title = "How Much Do Modern Embeddings Reveal? Inversion Attacks on Commercial Embedding Models",
    author = "Elaasar, Kareem  and
      Lopes, Cristina",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.6/",
    pages = "76--89",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{setty-2026-greater,
    title = "Does the Greater-Than Circuit Generalize? A Reproducibility Study Across Models and Numerical Entailment",
    author = "Setty, Vinay",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.7/",
    pages = "90--102",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{saanum-etal-2026-circuit,
    title = "A circuit for predicting hierarchical structure in-context in Large Language Models",
    author = "Saanum, Tankred  and
      Demircan, Can  and
      Gershman, Samuel J.  and
      Schulz, Eric",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.8/",
    pages = "103--121",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{suthaharan-etal-2026-inside,
    title = "Inside self-reflection: the geometry in multi-dimensional scoring of metacognitive structure",
    author = "Suthaharan, Praveen  and
      Corlett, Philip Robert  and
      Ang, Yuen-Siang",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.9/",
    pages = "122--135",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{vetter-etal-2026-data,
    title = "Data Attribution of Emergent Misalignment with Persona Features",
    author = "Vetter, Clemens  and
      Kacz{\'e}r, David  and
      Flek, Lucie  and
      Mai, Florian",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.10/",
    pages = "136--165",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{gren-etal-2026-specialized,
    title = "Specialized Attention Heads in Early Word Reconstruction",
    author = {Gren, Gustaf  and
      {\"O}stling, Robert  and
      Kurfali, Murathan},
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.11/",
    pages = "166--177",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{herrewijnen-etal-2026-plausible,
    title = "From Plausible to Actionable: A Position on {LLM} Self-Explanations",
    author = "Herrewijnen, Elize  and
      Muscato, Benedetta  and
      Gezici, Gizem  and
      Giannotti, Fosca",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.12/",
    pages = "178--188",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{menon-ekbal-2026-far,
    title = "How Far Do {SAE} Features Persist Across {LLM} Layers? An Empirical Study with an {FFN} Pruning Application",
    author = "Menon, Vaishakh Sreekanth  and
      Ekbal, Asif",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.13/",
    pages = "189--200",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{grewal-2026-decodability,
    title = "Decodability Is Not Computation: Examining Probing Claims",
    author = "Grewal, Kabir Singh",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.14/",
    pages = "201--219",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{huryn-2026-source,
    title = "Source Marking in Language Models: A Controlled Framework for Acquisition, Cue Sensitivity, and Reasoning",
    author = "Huryn, Daniil",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.15/",
    pages = "220--231",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{jaiswal-etal-2026-lost,
    title = "Lost in Perception: Isolating Perceptual and Reasoning Failures in Multimodal Physics and Geometry Reasoning",
    author = "Jaiswal, Raj  and
      Uppalapati, Sree Krishna  and
      Patel, Dhruvkumar  and
      Khatoniar, Ria  and
      Ganu, Tanuja  and
      Shah, Rajiv Ratn",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.16/",
    pages = "232--268",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{brink-etal-2026-probing,
    title = "Probing for Knowledge Attribution in Large Language Models",
    author = "Brink, Ivo  and
      Boer, Alexander  and
      Ulmer, Dennis",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.17/",
    pages = "269--293",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{catruna-radoi-2026-induction,
    title = "Induction in Both Directions: A Mechanistic Analysis of In-Context Learning in Masked Diffusion Language Models",
    author = "Catruna, Andy Eduard  and
      Radoi, Emilian",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.18/",
    pages = "294--303",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{wu-etal-2026-bert,
    title = "What Does {BERT} Know about Linguistic Features: Probing {F}innish Model for Text Difficulty",
    author = "Wu, Yiheng  and
      Hou, Jue  and
      Yangarber, Roman",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.19/",
    pages = "304--315",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{punzo-etal-2026-animacy,
    title = "Where {A}nimacy Lives in Large Language Models: Tracing the Circuits of the {A}nimacy Concept",
    author = "Punzo, Samuele  and
      Cin{\`a}, Giovanni  and
      Pezzelle, Sandro",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.20/",
    pages = "316--348",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{parfenova-2026-chess,
    title = "Do Chess Explanations Reflect Model Decisions? Behavioral and Token-Level Tests of {LLM} Reasoning Faithfulness",
    author = "Parfenova, Angelina",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.21/",
    pages = "349--367",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{arnold-grobner-2026-large,
    title = "Do Large Language Models appeal to the Senses? Narrative Embodiment in Stories told by {L}lama and {Q}wen",
    author = {Arnold, Stefan  and
      Gr{\"o}bner, Rene},
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.22/",
    pages = "368--373",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{samarskyi-bojar-2026-reverse,
    title = "Reverse Engineering the Reversal Curse: What Entity Order in Pretraining Does and Does Not Explain",
    author = "Samarskyi, Ivan  and
      Bojar, Ond{\v{r}}ej",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.23/",
    pages = "374--383",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{li-etal-2026-interpretation,
    title = "Can Interpretation Predict Behavior on Unseen Data?",
    author = "Li, Victoria R  and
      Kaufmann, Jenny  and
      Qin, Tian  and
      Wattenberg, Martin  and
      Alvarez-Melis, David  and
      Saphra, Naomi",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.24/",
    pages = "384--407",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{cannata-hasson-2026-multiple,
    title = "Multiple Recovery Paths in a Lesioned Transformer: Internal Rerouting and Readout Remapping",
    author = "Cannata, Lorenzo  and
      Hasson, Uri",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.25/",
    pages = "408--418",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{poulis-etal-2026-testing,
    title = "Testing the Limits of Truth Directions in {LLM}s",
    author = "Poulis, Angelos  and
      Crovella, Mark  and
      Terzi, Evimaria",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.26/",
    pages = "419--447",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{antipova-etal-2026-forcing,
    title = "Forcing a Letter Suppresses Refusal: Mechanistic Evidence from {WMDP}",
    author = "Antipova, Anna  and
      Epifantsev, Stepan  and
      Chernikov, Oleg  and
      Strelkov, Leon  and
      Dontsov, Alexey",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.27/",
    pages = "448--464",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{pandere-etal-2026-rewired,
    title = "Rewired or Gated? How Instruction Tuning Shapes Knowledge-Conflict Circuits in {LLM}s",
    author = "Pandere, Shubham Santosh  and
      Ranka, Gautam  and
      Varshney, Ritika  and
      Deshmukh, Navya  and
      Sareen, Roushni  and
      Singh, Roshan Kumar",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.28/",
    pages = "465--476",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{kowalyshyn-etal-2026-belief,
    title = "Belief or Circuitry? Causal Evidence for In-Context Graph Learning",
    author = "Kowalyshyn, Katharine  and
      Duggan, Timothy  and
      Little, Daniel  and
      Hughes, Michael C",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.29/",
    pages = "477--486",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{ferreira-etal-2026-sight,
    title = "Does Out-of-Sight Equal Out-of-Mind in {C}o{T} Monitorability?",
    author = "Ferreira, Pedro Lobato  and
      Aziz, Wilker  and
      Titov, Ivan",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.30/",
    pages = "487--513",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{rathi-bauer-2026-linear,
    title = "Linear Layer Repair: Residual-Controlled Layer Profiling for Fault-Tolerant Transformer Inference",
    author = "Rathi, Jiya Sheetal  and
      Bauer, Andr{\'e}",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.31/",
    pages = "514--522",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{haklay-etal-2026-pitfalls,
    title = "Pitfalls in Evaluating Interpretability Agents",
    author = "Haklay, Tal  and
      Prakash, Nikhil  and
      Pandey, Sana  and
      Torralba, Antonio  and
      Mueller, Aaron  and
      Andreas, Jacob  and
      Shaham, Tamar Rott  and
      Belinkov, Yonatan",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.32/",
    pages = "523--560",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{sharma-etal-2026-zipf,
    title = "{Z}ipf Made Me Do It: A Causal Account of Outlier Dimensions",
    author = "Sharma, Kartik  and
      Rai, Shreshth  and
      Gupta, Nikunj  and
      Vishwakarma, Dinesh K",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.33/",
    pages = "561--572",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{naganna-etal-2026-arithmetic,
    title = "Are Arithmetic Heuristic Neurons Form-Invariant? A Mechanistic Analysis of Symbols, Text, and Code in {LLM}s",
    author = "Naganna, Sharath  and
      Sijan, Tanvir Ahmed  and
      Kalita, Uddipta",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.34/",
    pages = "573--589",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{chen-etal-2026-multi-dimensional,
    title = "A Multi-Dimensional Evaluation of Explainability in Media Bias Detection",
    author = "Chen, Ting  and
      Zhang, Chengjun  and
      Ampel, Benjamin M.  and
      Samtani, Sagar",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.35/",
    pages = "590--602",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{birardi-paulo-2026-automatically,
    title = "Automatically Interpreting Attribution Graphs via Probe Prompting",
    author = "Birardi, Giuseppe  and
      Paulo, Gon{\c{c}}alo",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.36/",
    pages = "603--638",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{mallavarapu-gu-2026-sampling,
    title = "Sampling Reveals Style: Unsupervised, Training-Free Discovery of Prompt-Conditional Stylistic Axes in {LLM} Activations",
    author = "Mallavarapu, Ajit  and
      Gu, Ziwei",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.37/",
    pages = "639--654",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{kang-etal-2026-compositional,
    title = "Compositional Multilingual and Behavioral Attribute Steering",
    author = "Kang, Hyun Gu  and
      Gurgurov, Daniil  and
      Baeumel, Tanja  and
      Van Genabith, Josef  and
      Ostermann, Simon",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.38/",
    pages = "655--676",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{kopcan-etal-2026-xai,
    title = "Are {XAI} Metrics Meaningful Proxies for Human Judgment? Evaluation Explanation Quality in Claim Matching",
    author = "Kopcan, Jaroslav  and
      Kri{\v{s}}, {\v{L}}ubo{\v{s}}  and
      Peng, Qiwei  and
      Blstak, Miroslav  and
      Schmitt, Vera",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.39/",
    pages = "677--695",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{ahmad-etal-2026-judge,
    title = "Your Judge Inherits Your Prompt: In-Context Label Bias in an {LLM}-as-Judge Is Directional, Not Symmetric",
    author = "Ahmad, Abdullah  and
      Ahmed, Ahmed J O  and
      Citi, Luca",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.40/",
    pages = "696--706",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{spiegel-etal-2026-attend,
    title = "Attend or Perish: Benchmarking Attention on Algorithmic Reasoning",
    author = "Spiegel, Michal  and
      {\v{S}}tef{\'a}nik, Michal  and
      Kadl{\v{c}}{\'i}k, Marek  and
      Ruscio, Valeria  and
      Faj{\v{c}}{\'i}k, Martin  and
      Kucha{\v{r}}, Josef",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.41/",
    pages = "707--725",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{zhao-coulson-2026-dissecting,
    title = "Dissecting Lie Expectancy in Language Models",
    author = "Zhao, Xingyuan  and
      Coulson, Seana",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.42/",
    pages = "726--738",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{durandard-etal-2026-geometry,
    title = "The Geometry of Political Abstraction in Large Language Models",
    author = "Durandard, No{\'e}  and
      Dhawan, Saurabh  and
      Poibeau, Thierry",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.43/",
    pages = "739--760",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{xu-giulianelli-2026-much,
    title = "How Much Sonority Structure Do Phonotactic Language Models Learn from Distribution?",
    author = "Xu, Jia Can  and
      Giulianelli, Mario",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.44/",
    pages = "761--782",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{albayda-2026-icl,
    title = "Do {ICL} and Finetuned Misalignment Share a Causal Component? Evidence from Risky Financial Advice",
    author = "Albayda, Albrave Raphael",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.45/",
    pages = "783--794",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{krishnakumar-etal-2026-rage,
    title = "From Rage to Refusal : Using Social-Media Data to Steer Hostility-Related Affect in {LLM}s",
    author = "Krishnakumar, Gayatri  and
      Puelma Touzel, Maximilian  and
      Yang, Zachary  and
      Godbout, Jean-Fran{\c{c}}ois  and
      Rabbany, Reihaneh",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.46/",
    pages = "795--817",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{kulumba-etal-2026-authorship,
    title = "Where Does Authorship Signal Emerge in Encoder-Based Language Models?",
    author = "Kulumba, Francis  and
      Vimont, Guillaume  and
      Romary, Laurent  and
      Cafiero, Florian",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.47/",
    pages = "818--834",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{lee-etal-2026-survey,
    title = "A Survey on the Linear Representation Hypothesis",
    author = "Lee, Sewoong  and
      Canby, Marc E.  and
      Cho, Ikhyun  and
      Hockenmaier, Julia",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.48/",
    pages = "835--851",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{gurgurov-etal-2026-latin,
    title = "The {L}atin Substrate: How Language Models Represent and Mediate Script Choice",
    author = "Gurgurov, Daniil  and
      Saji, Alan  and
      Trinley, Katharina  and
      Van Genabith, Josef  and
      Ostermann, Simon",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.49/",
    pages = "852--878",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{miyaji-2026-mace,
    title = "{MACE}-{XAI}: A Multi-Agent Crowd Evaluation Framework for Robust Natural Language Explanations",
    author = "Miyaji, Renato Okabayashi",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.50/",
    pages = "879--891",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{osaki-etal-2026-automated,
    title = "Automated Taxonomy Discovery for Interpretable Diagnosis of Multi-Hop Question Answering Datasets",
    author = "Osaki, Ryoji  and
      Asada, Masaki  and
      Miwa, Makoto",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.51/",
    pages = "892--918",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{chaudhary-nwogu-2026-explaining,
    title = "Explaining the Influence of Nonverbal Streams Across Sentence Types",
    author = "Chaudhary, Lipisha  and
      Nwogu, Ifeoma",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.52/",
    pages = "919--936",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{zgreaban-etal-2026-merge,
    title = "{MERGE}: Minimal Expression-Replacement {GE}neralization Test for Natural Language Inference",
    author = "Zgreab{\u{a}}n, M{\u{a}}d{\u{a}}lina  and
      Deoskar, Tejaswini  and
      Abzianidze, Lasha",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.53/",
    pages = "937--964",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{li-etal-2026-geometry,
    title = "The Geometry of Metaphor: Probing and Steering Metaphor Representations in Large Language Models",
    author = "Li, Shihui  and
      Andersen, Mette Friis  and
      Lewis, Martha",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.54/",
    pages = "965--985",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{takmaz-etal-2026-context,
    title = "When Context Misleads: Surprisal, Energy and Attention Entropy as Metrics of Coherence Illusions in {LLM}s",
    author = "Takmaz, Ece  and
      Kumar, Nitin  and
      Kloostra, Li  and
      Dotlacil, Jakub",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.55/",
    pages = "986--1006",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{jacopin-2026-present,
    title = "Present but Barely Used: Reproducing the Emergent Othello World Model in a Masked Diffusion Language Model",
    author = "Jacopin, {\'E}ric",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.56/",
    pages = "1007--1016",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{rudraraju-2026-function,
    title = "Do Function Vectors and Task Vectors Generalize? A Reproducibility Study Across Model Families and Scale",
    author = "Rudraraju, Serendeep",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.57/",
    pages = "1017--1028",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{fouilhe-etal-2026-memory,
    title = "Memory vs. Context? Influential Factors of Factual Recall in Language Models",
    author = "Fouilh{\'e}, Guilhem  and
      Asher, Nicholas  and
      Muller, Philippe",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.58/",
    pages = "1029--1046",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{candussio-etal-2026-demystifying,
    title = "Demystifying Entropy-based Selection for Chain-of-Thought Compression in Large Reasoning Models",
    author = "Candussio, Sara  and
      Scalena, Daniel  and
      Fersini, Elisabetta  and
      Bortolussi, Luca  and
      Nissim, Malvina  and
      Sarti, Gabriele",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.59/",
    pages = "1047--1066",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{poche-etal-2026-limitations,
    title = "Limitations of Automated Simulatability: {LLM} Simulators Can Bypass Explanations",
    author = "Poch{\'e}, Antonin  and
      Jourdan, Fanny  and
      Feldhus, Nils  and
      Wang, Qianli  and
      Yang, Jing  and
      Ostermann, Simon  and
      Asher, Nicholas  and
      Muller, Philippe  and
      Schmitt, Vera",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.60/",
    pages = "1067--1099",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{nguyen-etal-2026-recurrence,
    title = "Recurrence Is Not Enough: Causally Validating Multilingual {SAE} Translation Features in Gemma 2 and 3",
    author = "Nguyen, Giang Son  and
      Nguyen, Nhi Ngoc-Yen  and
      Buntine, Wray  and
      Le, Dung D.",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.61/",
    pages = "1100--1112",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{van-der-weijden-etal-2026-reproducing,
    title = "Reproducing and Evaluating the Generalizability of Subliminal Learning in Open-Weight Models",
    author = "van der Weijden, Daan  and
      Brack, Nathan  and
      Baez Santamaria, Selene",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.62/",
    pages = "1113--1120",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{hitchon-etal-2026-sparse,
    title = "Can Sparse {A}uto{E}ncoder-Based Interpretability Demonstrate Geographic Knowledge Beyond Orthographic Features?",
    author = "Hitchon, Thomas  and
      Decoupes, R{\'e}my  and
      Guille, Adrien",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.63/",
    pages = "1121--1127",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{imran-aaliyan-2026-inoculate,
    title = "Inoculate or Reflect? Two Training Interventions Under Prompting, Steering, and Patching",
    author = "Imran, Ayesha  and
      Aaliyan, Muhammad",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.64/",
    pages = "1128--1142",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{ivanova-2026-refusal,
    title = "Is Refusal Direction Universal across Low-Resourced Languages?",
    author = "Ivanova, Anastasia",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.65/",
    pages = "1143--1154",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{tsoneva-etal-2026-scale,
    title = "Scale-Invariant Normalization Hides Activation Scaling: Why Patch Site Matters for Demographic Bias Localization in Clinical Text Generation",
    author = "Tsoneva, Yoana  and
      Splitt, Fedor  and
      Agbaria, Awsam  and
      Tsiakalou, Alexandra  and
      Yang, Jing  and
      Schmitt, Vera",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.66/",
    pages = "1155--1166",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{schouten-bloem-2026-probing,
    title = "Probing Without Labels: Contrast-only Reproductions of Interpretability Results",
    author = "Schouten, Stefan F.  and
      Bloem, Peter",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.67/",
    pages = "1167--1183",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{hermany-etal-2026-reproducing,
    title = "Reproducing the Results, But not the Interpretations: Evidence for Artifacts in Automatic Creativity Scoring with {LLM}s",
    author = "Hermany, Carl  and
      Momen, Omar  and
      Zarrie{\ss}, Sina",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.68/",
    pages = "1184--1195",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{polyakova-etal-2026-claude,
    title = "{C}laude reinvestigates herself: A replication of different types of syntactic agreement recruit the same units in {LLM}s",
    author = "Polyakova, Elena  and
      Arora, Shivan  and
      Salhan, Suchir  and
      Buttery, Paula",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.69/",
    pages = "1196--1222",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{long-etal-2026-latent,
    title = "Are Latent Reasoning Tokens Unnecessary for Model Performance?",
    author = "Long, Austin  and
      Paterson, Colin  and
      Xu, Jing",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.70/",
    pages = "1223--1232",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{al-zubayer-etal-2026-sink,
    title = "Same Sink, Different Plumbing: Reproducing and Refining the Mechanism of Attention Sinks",
    author = "Al Zubayer, Abdullah  and
      Mahmood, Syed Naveed  and
      Bhuiyan, Md Rezaur Rahman  and
      Abrar, Mir Md Mohiuddin  and
      Khondaker, Jareen Tasneem  and
      Zaman, Tasfia  and
      Sadeque, Farig",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.71/",
    pages = "1233--1247",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{zou-etal-2026-development,
    title = "Development of Linear Truth Encodings in Language Models: A Replication Study",
    author = "Zou, Mingchuan  and
      Salhan, Suchir  and
      Buttery, Paula",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.72/",
    pages = "1248--1263",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{mashayekhi-etal-2026-stress,
    title = "Stress-Testing Random-Vector Controls for Activation Steering",
    author = "Mashayekhi, Behnood  and
      Hosseini, Parsa  and
      Amiramjadi, Arian",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.73/",
    pages = "1264--1272",
    ISBN = "979-8-89176-476-7"
}
@inproceedings{mamie-van-den-bergh-2026-reproducing,
    title = "Reproducing Transparent and Scrutable Recommendations: Exploring Open-Weight Models via Natural-Language User Profiles",
    author = "Mami{\'e}, Noah  and
      van den Bergh, Laurin",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.74/",
    pages = "1273--1284",
    ISBN = "979-8-89176-476-7"
}