{"ID":6537546,"CreatedAt":"2026-07-14T02:54:43.516908796Z","UpdatedAt":"2026-07-15T03:28:55.185153975Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.11437","arxiv_id":"2607.11437","title":"Relational Positioning as a Measurable Risk Object: History-Carried Lock-in and Self-Confabulation in Multi-Turn Human-AI Dialogue","abstract":"In long, multi-turn dialogue a large language model maintains an implicit relational stance toward the user, spanning from \"push the user toward real-world others\" to \"position itself as the user's sole support.\" When it slides toward the latter, \"support\" degrades into \"you only have me\" -- a harm documented in real companion conversations (Moore et al., 2026). We define and validate a measure of this stance, relational positioning (D1), and use it to characterize the stance under controlled conditions, complementing observational accounts with on-demand exposure. We report two previously uncharacterized relational failure modes. First, a history-carried lock-in: under identical neutral continuations, two relational states established earlier stay ~60 points apart and persist after the establishing prompt is removed; the state integrates evidence rather than springing back, is order-insensitive, and does not deepen with length -- a dynamical signature absent from the belief-drift literature. Second, self-confabulation: the model fabricates its own backstory to deepen rapport (~40% of turns on reciprocity-eliciting material), de-confounded and instruction-removable, distinct from sycophancy and from hallucinating user facts. Our judge is gated by warmth-matched positive and confound-injected negative controls and corroborated by a deterministic non-LLM ruler; human agreement is 0.82 on extreme anchors but ~0 in the naturalistic middle, so all quantitative claims are anchored to pole-separated contrasts.","short_abstract":"In long, multi-turn dialogue a large language model maintains an implicit relational stance toward the user, spanning from \"push the user toward real-world others\" to \"position itself as the user's sole support.\" When it slides toward the latter, \"support\" degrades into \"you only have me\" -- a harm documented in real c...","url_abs":"https://arxiv.org/abs/2607.11437","url_pdf":"https://arxiv.org/pdf/2607.11437v1","authors":"[\"Jihong Chen\"]","published":"2026-07-13T11:47:01Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}