5 papers
Personalized Deep Research Query Refinement with Graph-Scaffolded Evidence Grounding
Soojin Yoon, Dongha Lee
User requests serve as research specifications for deep research agents, shaping what evidence to seek and how to synthesize it. In personalized deep research, these specifications…
MVIGER: Multi-View Variational Integration of Complementary Knowledge for Generative Recommender
Tongyoung Kim, Soojin Yoon, SeongKu Kang +2
Language Models (LMs) have been widely used in recommender systems to incorporate textual information of items into item IDs, leveraging their advanced language understanding and g…
IPQA: A Benchmark for Core Intent Identification in Personalized Question Answering
Jieyong Kim, Maryam Amirizaniani, Soojin Yoon +1
Intent identification serves as the foundation for generating appropriate responses in personalized question answering (PQA). However, existing benchmarks evaluate only response qu…
Towards Personalized Conversational Sales Agents: Contextual User Profiling for Strategic Action
Tongyoung Kim, Jeongeun Lee, Soojin Yoon +2
Conversational Recommender Systems (CRSs)aim to engage users in dialogue to provide tailored recommendations. While traditional CRSs focus on eliciting preferences and retrieving i…
Unsupervised Robust Cross-Lingual Entity Alignment via Neighbor Triple Matching with Entity and Relation Texts
Soojin Yoon, Sungho Ko, Tongyoung Kim +3
Cross-lingual entity alignment (EA) enables the integration of multiple knowledge graphs (KGs) across different languages, providing users with seamless access to diverse and compr…