collaborators

19 papers

cs.AI2026

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…

cs.CL2026

Region4Web: Rethinking Observation Space Granularity for Web Agents

Donguk Kwon, Dongha Lee

Web agents perceive web pages through an observation space, yet its granularity has remained an underexamined design choice. Existing work treats observation at the same element-le…

cs.IR2026

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…

cs.IR2026

Why These Documents? Explainable Generative Retrieval with Hierarchical Category Paths

Sangam Lee, Ryang Heo, SeongKu Kang +3

Generative retrieval directly decode a document identifier (i.e., docid) in response to a query, making it impossible to provide users with explanations as an answer for ``why is t…

cs.CL2026

CONDESION-BENCH: Conditional Decision-Making of Large Language Models in Compositional Action Space

Yeonjun Hwang, Sungyong Park, Minju Kim +2

Large language models have been widely explored as decision-support tools in high-stakes domains due to their contextual understanding and reasoning capabilities. However, existing…

cs.CL2026

Quantifying Genuine Awareness in Hallucination Prediction Beyond Question-Side Shortcuts

Yeongbin Seo, Dongha Lee, Jinyoung Yeo

Many works have proposed methodologies for language model (LM) hallucination detection and reported seemingly strong performance. However, we argue that the reported performance to…