@inproceedings{wang-etal-2026-causaldetox,
    title = "{C}ausal{D}etox: Causal Head Selection and Intervention for Language Model Detoxification",
    author = "Wang, Yian  and
      Chen, Yuen  and
      Goyal, Agam  and
      Sundaram, Hari",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.577/",
    pages = "11893--11914",
    ISBN = "979-8-89176-395-1",
    abstract = "Large language models (LLMs) frequently generate toxic content, posing significant risks for safe deployment. Current mitigation strategies often degrade generation quality or require costly human annotation. We propose CausalDetox, a framework that identifies and intervenes on the specific attention heads causally responsible for toxic generation. Using the Probability of Necessity and Sufficiency (PNS), we isolate a minimal set of heads that are necessary and sufficient for toxicity. We utilize these components via two complementary strategies: (1) Local Inference-Time Intervention, which constructs dynamic, input-specific steering vectors for context-aware detoxification, and (2) PNS-Guided Fine-Tuning, which permanently unlearns toxic representations. We also introduceParaTox, a novel benchmark of aligned toxic/non-toxic sentence pairs enabling controlled counterfactual evaluation. Experiments on ToxiGen, ImplicitHate, and ParaDetox show that CausalDetox achieves up to 5.34{\%} greater toxicity reduction compared to baselines while preserving linguistic fluency, and offers a $7\times$ speedup in head selection."
}