# Relational Positioning as a Measurable Risk Object: History-Carried Lock-in and Self-Confabulation in Multi-Turn Human-AI Dialogue

arXiv: https://arxiv.org/abs/2607.11437 · HTML: https://mlsanity.com/paper/2607.11437/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 16 references that are in the map.
- First posted on arXiv 13 Jul 2026.

## Builds on (most cited first, 15 of 15)

- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Towards Emotional Support Dialog Systems](https://mlsanity.com/paper/2106.01144/) (2021)
- [Sycophancy Is Not One Thing: Causal Separation of Sycophantic Behaviors in LLMs](https://mlsanity.com/paper/2509.21305/) (2025)
- [Accumulating Context Changes the Beliefs of Language Models](https://mlsanity.com/paper/2511.01805/) (2025)
- [Characterizing Delusional Spirals through Human-LLM Chat Logs](https://mlsanity.com/paper/2603.16567/) (2026)
- [Drift No More? Context Equilibria in Multi-Turn LLM Interactions](https://mlsanity.com/paper/2510.07777/) (2025)
- [Neural steering vectors reveal dose and exposure-dependent impacts of human-AI relationships](https://mlsanity.com/paper/2512.01991/) (2025)
- [Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactions](https://mlsanity.com/paper/2512.12775/) (2025)
- [Attractor States Emerge in Multi-Turn LLM Conversations](https://mlsanity.com/paper/2606.30571/) (2026)
- [CURATe: Benchmarking Personalised Alignment of Conversational AI Assistants](https://mlsanity.com/paper/2410.21159/) (2024)
- [Robot-Led Vision Language Model Wellbeing Assessment of Children](https://mlsanity.com/paper/2504.02765/) (2025)
- [The Dynamics of Delusion: Modeling Bidirectional False Belief Amplification in Human-Chatbot Dialogue](https://mlsanity.com/paper/2604.25096/) (2026)
- [Know You Before You Speak: User-State Modeling for LLM Personalization in Multi-Turn Conversation](https://mlsanity.com/paper/2605.24647/) (2026)
- [Identity as Attractor: Geometric Evidence for Persistent Agent Architecture in LLM Activation Space](https://mlsanity.com/paper/2604.12016/) (2026)
- [MIRROR: Converging Cognitive Principles as Computational Mechanisms for AI Reasoning](https://mlsanity.com/paper/2506.00430/) (2025)

## Abstract (arXiv)

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.