@inproceedings{demeocq-etal-2026-attachment,
    title = "The Attachment Index: Auditing Attachment Language Cues and Relational Safety Risks in Human-{LLM} Dialogue",
    author = {Demeocq, Cyndie  and
      Prasad, Animesh  and
      Saeidi, Marzieh  and
      Goodall, Karen  and
      Ross, Bj{\"o}rn},
    editor = "Zirikly, Aya  and
      Bar, Kfir  and
      MacAvaney, Sean  and
      Ireland, Molly  and
      Ophir, Yaakov  and
      Atzil-Slonim, Dana  and
      Varadarajan, Vasudha  and
      Bedrick, Steven  and
      Desmet, Bart",
    booktitle = "Proceedings of the 10th Workshop on Computational Linguistics and Clinical Psychology ({CLP}sych 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.clpsych-1.26/",
    pages = "324--339",
    ISBN = "979-8-89176-421-7",
    abstract = "As conversational AI systems grow increasingly toward emotional support contexts, relational safety failures between users and chatbot remain under-measured. We present a psycholinguistic grounded framework for auditing attachment-relevant language cues. Our approach identifies when an LLM{'}s replies exhibit linguistic attachment cues and surface related patterns that may signal parasocial bonding, including anthropomorphism or over-dependence. We adapt the Adult Attachment Interview into two complementary, automatable lenses - attachment cues features and Gricean maxims - and combine them with psychologist-led annotation of multi-turn persona dialogues. Applying this framework, we observe that models can align with persona-intended attachment cue patterns. We also find that judge-LLMs alone are unreliable, highlighting the need for psychologist-in-the-loop evaluation. The 25 psychologist-led annotated conversations revealed risks, including boundary blurring and missed opportunities for appropriate referral or triage. These insights motivate attachment-aware safeguards - such as non-personification, boundary language, and explicit referral mechanisms - to reduce mis-attunement and over-attachment in LLM conversational settings."
}