works on
conversation safety 1dialogue systems 1evaluation metrics 1large language models 1relational stance 1risk assessment 1

From the 1 of 1 linked paper with an AI index.

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2026

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

Jihong Chen

The paper introduces a metric for measuring how a large language model positions itself relationally in multi‑turn conversations and identifies two risk patterns: a persistent "loc…