Yeonghwan Jeon
Research Subjects
Yeonghwan Jeon has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Changho Lee
LG Uplus Corp., Seoul, Republic of Korea
1 shared publication - Hyuncheol Jo
LG Uplus Corp., Seoul, Republic of Korea
1 shared publication - Jinmo Kang
LG Uplus Corp., Seoul, Republic of Korea
1 shared publication - Junho Shin
LG Uplus Corp., Seoul, Republic of Korea
1 shared publication - MinSeop Lee
School of Electrical Engineering, Korea University, Seoul 02841, Korea
1 shared publication - Songha Kim
LG Uplus Corp., Seoul, Republic of Korea
1 shared publication
Latest Publications
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 4700-4705
PersonaPlugin: A Multi-Source Persona Framework for LLM Personalization in Telecommunications
Personalizing large language model (LLM) responses in enterprise environments faces unique challenges: heterogeneous data sources, strict on-premise constraints, and unreliable LLM outputs. We present PersonaPlugin, a production-ready framework that transforms real-world telecom signals—call summaries, app usage, and location patterns—into structured personas for LLM personalization. Our system processes 1M+ behavioral records daily, entirely on-premise. The framework comprises three specialized engines, with the call extraction engine achieving >99% parsing success through cascaded fallback mechanisms. We conduct a comprehensive two-track evaluation: (1) general personalization across 800 scenarios, and (2) call-context personalization across 400 scenarios. Our LLM-as-a-Judge evaluation, validated against human judgments (κ=0.71), demonstrates that persona injection significantly improves personalization: +24.0% in P-Score and +26.7% in Adherence over baseline. Integrating call context with personas yields +11% additional improvement, validating the synergistic value of multi-source persona construction.
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 4700-4705
Open AccessPersonaPlugin: A Multi-Source Persona Framework for LLM Personalization in Telecommunications
Personalizing large language model (LLM) responses in enterprise environments faces unique challenges: heterogeneous data sources, strict on-premise constraints, and unreliable LLM outputs. We present PersonaPlugin, a production-ready framework that transforms real-world telecom signals—call summaries, app usage, and location patterns—into structured personas for LLM personalization. Our system processes 1M+ behavioral records daily, entirely on-premise. The framework comprises three specialized engines, with the call extraction engine achieving >99% parsing success through cascaded fallback mechanisms. We conduct a comprehensive two-track evaluation: (1) general personalization across 800 scenarios, and (2) call-context personalization across 400 scenarios. Our LLM-as-a-Judge evaluation, validated against human judgments (κ=0.71), demonstrates that persona injection significantly improves personalization: +24.0% in P-Score and +26.7% in Adherence over baseline. Integrating call context with personas yields +11% additional improvement, validating the synergistic value of multi-source persona construction.