@inproceedings{doan-etal-2026-causal,
    title = "Causal Activation Steering via Sparse Mediation",
    author = "Doan, Toan  and
      Le, Uyen  and
      Nguyen, Thin",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.findings-eacl.57/",
    pages = "1079--1097",
    ISBN = "979-8-89176-386-9",
    abstract = "Activation steering or editing hidden states to control language-model behavior can be framed as a causal mediation problem: inputs induce internal activations, a subset of which act as mediators transmitting targeted behaviors to outputs. We formalize a structural graph over transformer layers and derive front-door{---}style identification conditions that justify steering through mediating subspaces while preserving non-mediating features, thereby reducing confounding and off-target effects. Within this mediation-first view, we present CAS-BiPO, a sparse mediation steering approach that learns targeted behavioral interventions via regularized training. Empirically, our method achieves 97-100{\%} of dense baseline effectiveness across four behavioral control tasks while using only 10-30{\%} of activation dimensions. Learned masks concentrate 94.3{\%} of steering effects in 26.7{\%} of dimensions, with neurons exhibiting 2.2$\times$ higher activation changes, validating the sparse mediation hypothesis. Our causal framework provides theoretical grounding while CAS-BiPO demonstrates that end-to-end learning of interpretable, reliable interventions is both feasible and advantageous."
}