Skip to content

The Illusion of Progress: Dialogue-Derived Signals for Proactive Intervention Timing in Student–GenAI Interaction

· 0 citations · 24 references

TL;DR

This work argues for a restraint-first intervention policy: systems should intervene not merely because dialogue appears active, but when sustained engagement fails to convert into observable enactment, while withholding intervention once concrete enactment cues are present.

View source

Similar papers

Book Open access Oct 2026

From Dialogue to Decision: A Traceability-Oriented Framework for Studying Language-Mediated Coordination

Digital markets offer a useful setting for examining how language becomes part of socio-technical coordination. Yet even in simulation, it is difficult to see how a conversational cue moves from exposure to memory, reasoning, and action. This poster introduces Financial Town, a traceability-oriented generative multi-ag...

Yong-Sheng Chi, Ming-Xuan Liu, Yee-Hung Hong et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Clarification Is Not Correction: LLMs Fail to Let Go

Research for interactive LLMs from retaining more context toward preserving uncertainty is redirected from retaining more context toward preserving uncertainty, to motivate uncertainty-preserving state management.

Jian-Zhe Lin, Xiao-Lin Li, Fei Wang et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Enforcing Narrative Reliability and Epistemic Pacing in LLM-Driven Detective Games via Structured Knowledge Trees

A Structured Knowledge Tree architecture coupled with a tri-agent LLM pipeline for controlling dialogue in an open-ended interrogation game and demonstrates that the structured architecture reduces critical hallucinations by 64.78% and entirely prevents premature narrative disclosure.

Parsa Rahmati, Richard Zhao · 0 citations
#human-computer interacti... Preprint Sep 2026

Prompting Against Persona Drift: Comparing Intervention Timing and Content in LLM-Simulated Conversations

Simulating student personas with large language models (LLMs) enables scalable evaluation of educational systems. However, behavioral drift, a progressive decline in persona consistency, can emerge over extended conversations, limiting the validity of such simulations. We evaluate five prompt-level mechanisms using sep...

Nicolas Leins, Jennifer Haase, Varvara Geronimus et al. · 0 citations
#human-computer interacti... Preprint Oct 2026

Proactive AI: From Turns to Replannable Dialogue Timelines

Conventional large-language-model chat interfaces typically follow user-initiated turns: each request elicits a response, after which the system waits for further input. Human asynchronous communication instead unfolds over time through message bursts, delays, silence, resumed topics, and self-initiated contact. Proact...

Zi-Jie Yang · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.