paper-with-me

홈 › Papers

R-CAGE: A Structural Model for Emotion Output Design in Human-AI Interaction

2025-05-11 · Suyeon Choi

This paper presents R-CAGE (Rhythmic Control Architecture for Guarding Ego), a theoretical framework for restructuring emotional output in long-term human-AI interaction. While prior affective computing approaches emphasized expressiveness, immersion, and responsiveness, they often neglected the cognitive and structural consequences of repeated emotional engagement. R-CAGE instead conceptualizes emotional output not as reactive expression but as ethical design structure requiring architectural intervention. The model is grounded in experiential observations of subtle affective symptoms such as localized head tension, interpretive fixation, and emotional lag arising from prolonged interaction with affective AI systems. These indicate a mismatch between system-driven emotion and user interpretation that cannot be fully explained by biometric data or observable behavior. R-CAGE adopts a user-centered stance prioritizing psychological recovery, interpretive autonomy, and identity continuity. The framework consists of four control blocks: (1) Control of Rhythmic Expression regulates output pacing to reduce fatigue; (2) Architecture of Sensory Structuring adjusts intensity and timing of affective stimuli; (3) Guarding of Cognitive Framing reduces semantic pressure to allow flexible interpretation; (4) Ego-Aligned Response Design supports self-reference recovery during interpretive lag. By structurally regulating emotional rhythm, sensory intensity, and interpretive affordances, R-CAGE frames emotion not as performative output but as sustainable design unit. The goal is to protect users from oversaturation and cognitive overload while sustaining long-term interpretive agency in AI-mediated environments.

📄 PDF Abstract BibTeX arXiv:2505.07020

Code (0)

등록된 구현이 없습니다.

Tasks

Rhythm

Similar Papers 제목 키워드 기반

CAGE: Bridging the Accuracy-Aesthetics Gap in Educational Diagrams via Code-Anchored Generative Enhancement

2026-04-06 · Dikshant Kukreja, Kshitij Sah, Karan Goyal, Mukesh Mohania 외 arxiv

Educational diagrams -- labeled illustrations of biological processes, chemical structures, physical systems, and mathematical concepts -- are essential cognitive tools in K-12 instruction. Yet no existing method can gen…

CAGE: Cognitive Attribution Graphs for Faithful Inline Citation Generation in Long-Form Question Answering

2026-07-27 · Zhichao Yan, Shizhao Li, Jiapu Wang, Haoran Luo 외 arxiv

Long-form question answering increasingly relies on retrieved evidence to make LLM outputs verifiable, with inline citations tracing claims to source documents. However, existing systems often attach citations that are t…

Question AnsweringAnswer Generation

Multifidelity digital twin for real-time monitoring of structural dynamics in aquaculture net cages

2024-06-06 · Eirini Katsidoniotaki, Biao Su, Eleni Kelasidi, Themistoklis P. Sapsis

As the global population grows and climate change intensifies, sustainable food production is critical. Marine aquaculture offers a viable solution, providing a sustainable protein source. However, the industry's expansi…

AI shares emotion with humans across languages and cultures

2025-06-11 · Xiuwen Wu, Hao Wang, Zhiang Yan, Xiaohan Tang 외

Effective and safe human-machine collaboration requires the regulated and meaningful exchange of emotions between humans and artificial intelligence (AI). Current AI systems based on large language models (LLMs) can prov…

CAGE-GS: High-fidelity Cage Based 3D Gaussian Splatting Deformation

2025-04-17 · Yifei Tong, Runze Tian, Xiao Han, Dingyao Liu 외

As 3D Gaussian Splatting (3DGS) gains popularity as a 3D representation of real scenes, enabling user-friendly deformation to create novel scenes while preserving fine details from the original 3DGS has attracted signifi…

3DGS