3 papers
cs.IR2026
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…
cs.IR2026
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…
cs.IR2026
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…