From Stateless to Situated: Building a Psychological World for LLM-Based Emotional Support
Boning Zhao, Clover Hu, Xinnuo Li

TL;DR
This paper introduces LEKIA 2.0, a new LLM architecture that maintains a persistent external situational model to improve multi-turn emotional support, addressing the statelessness of traditional models and enhancing stability and control.
Contribution
LEKIA 2.0 decouples situational modeling from intervention, enabling stable, controllable multi-turn emotional support with an innovative evaluation protocol.
Findings
31% improvement over prompt-only baselines
Effective maintenance of user situation and consent boundaries
Enhanced stability and control in emotional support interactions
Abstract
In psychological support and emotional companionship scenarios, the core limitation of large language models (LLMs) lies not merely in response quality, but in their reliance on local next-token prediction, which prevents them from maintaining the temporal continuity, stage awareness, and user consent boundaries required for multi-turn intervention. This stateless characteristic makes systems prone to premature advancement, stage misalignment, and boundary violations in continuous dialogue. To address this problem, we argue that the key challenge in process-oriented emotional support is not simply generating natural language, but constructing a sustainably updatable external situational structure for the model. We therefore propose LEKIA 2.0, a situated LLM architecture that separates the cognitive layer from the executive layer, thereby decoupling situational modeling from intervention…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNeurobiology of Language and Bilingualism · Mental Health via Writing · Topic Modeling
