6 papers
SPRInG: Continual LLM Personalization via Selective Parametric Adaptation and Retrieval-Interpolated Generation
Seoyeon Kim, Jaehyung Kim
Personalizing Large Language Models typically relies on static retrieval or one-time adaptation, assuming user preferences remain invariant over time. However, real-world interacti…
Rethinking Test-Time Scaling for Medical AI: Model and Task-Aware Strategies for LLMs and VLMs
Gyutaek Oh, Seoyeon Kim, Sangjoon Park +1
Test-time scaling has recently emerged as a promising approach for enhancing the reasoning capabilities of large language models or vision-language models during inference. Althoug…
IEA-Plugin: An AI Agent Reasoner for Test Data Analytics
Seoyeon Kim, Yu Su, Li-C. Wang
This paper introduces IEA-plugin, a novel AI agent-based reasoning module developed as a new front-end for the Intelligent Engineering Assistant (IEA). The primary objective of IEA…
Can Code-Switched Texts Activate a Knowledge Switch in LLMs? A Case Study on English-Korean Code-Switching
Seoyeon Kim, Huiseo Kim, Chanjun Park +2
Recent large language models (LLMs) demonstrate multilingual abilities, yet they are English-centric due to dominance of English in training corpora. The limited resource for low-r…
Commonsense-augmented Memory Construction and Management in Long-term Conversations via Context-aware Persona Refinement
Hana Kim, Kai Tzu-iunn Ong, Seoyeon Kim +2
Memorizing and utilizing speakers' personas is a common practice for response generation in long-term conversations. Yet, human-authored datasets often provide uninformative person…
VerifiNER: Verification-augmented NER via Knowledge-grounded Reasoning with Large Language Models
Seoyeon Kim, Kwangwook Seo, Hyungjoo Chae +2
Recent approaches in domain-specific named entity recognition (NER), such as biomedical NER, have shown remarkable advances. However, they still lack of faithfulness, producing err…