13 papers
PGMem: Tightly Coupled Persona-Memory Graph for Lifelong Personalized Agents
Wonjun Choi, Yerim Kim, Yukyung Lee +1
Long-term personalized dialogue agents must track user preferences as their personas evolve. Existing memory systems organize past events well, but store personas as flat profiles…
HiVe: Beyond Static Prompts for Multitask Learning via Hierarchy-based Vertical Mixture-of-Experts
Hyeonjik Bae, Minyeol Kim, Susik Yoon
As large language models (LLMs) continue to scale, parameter-efficient fine-tuning (PEFT) has become a practical alternative to full-parameter adaptation. Prompt tuning is effectiv…
PEARL: Front-Loading Relational Chains for Multi-Hop Table Retrieval
Subeen Ho, Hyeongu Kang, SeongKu Kang +1
While large language models (LLMs) have shown strong capabilities in tabular reasoning, retrieving relevant tables remains challenging due to the fragmented and relational structur…
Beyond Observed Auxiliary Relations: Environment-Conditioned Modeling for Multi-Behavior Recommendation
Seunghan Lee, Hyunsik Yoo, Jian Kang +2
Multi-behavior recommendation (MBR) leverages auxiliary behavioral signals, such as clicks and add-to-cart, to enhance target behavior prediction like purchases. While recent graph…
Segment-driven Structural Induction and Semantic Alignment for Heterogeneous Tabular Representation
Woojun Jung, Susik Yoon
Real-world domains often contain heterogeneous tables whose headers vary while their underlying attribute semantics are shared, making it difficult to induce domain-specialized sem…
MUDY: Multi-Granular Dynamic Candidate Contextualization for Unsupervised Keyphrase Extraction
Hyeongu Kang, Susik Yoon
Keyphrase extraction aims to automatically identify concise phrases that effectively represent the content of a document. While recent methods leveraging pre-trained language model…
Can Structural Cues Save LLMs? Evaluating Language Models in Massive Document Streams
Yukyung Lee, Yebin Lim, Woojun Jung +2
Evaluating language models in streaming environments is critical, yet underexplored. Existing benchmarks either focus on single complex events or provide curated inputs for each qu…
CREAM: Continual Retrieval on Dynamic Streaming Corpora with Adaptive Soft Memory
HuiJeong Son, Hyeongu Kang, Sunho Kim +4
Information retrieval (IR) in dynamic data streams is a crucial task, as shifts in data distribution degrade the performance of AI-powered IR systems. To mitigate this issue, memor…
Improving Scientific Document Retrieval with Academic Concept Index
Jeyun Lee, Junhyoung Lee, Wonbin Kweon +7
Adapting general-domain retrievers to scientific domains is challenging due to the scarcity of large-scale domain-specific relevance annotations and the substantial mismatch in voc…
Building UI/UX Dataset for Dark Pattern Detection and YOLOv12x-based Real-Time Object Recognition Detection System
Se-Young Jang, Su-Yeon Yoon, Jae-Woong Jung +6
With the accelerating pace of digital transformation and the widespread adoption of online platforms, both social and technical concerns regarding dark patterns-user interface desi…
Multi-level Diagnosis and Evaluation for Robust Tabular Feature Engineering with Large Language Models
Yebin Lim, Susik Yoon
Recent advancements in large language models (LLMs) have shown promise in feature engineering for tabular data, but concerns about their reliability persist, especially due to vari…
SPRINT: Scalable and Predictive Intent Refinement for LLM-Enhanced Session-based Recommendation
Gyuseok Lee, Wonbin Kweon, Zhenrui Yue +5
Large language models (LLMs) have enhanced conventional recommendation models via user profiling, which generates representative textual profiles from users' historical interaction…
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…