J. Lee

Co-Attention Graph Pooling for Efficient Pairwise Graph Interaction Learning

2023 · IEEE Access

Graph Neural Networks (GNNs) have proven to be effective in processing and learning from graph-structured data. However, previous works mainly focused on understanding single graph inputs while many real-world applications require pair-wise analysis for graph-structured …

Re-Ex: Revising after Explanation Reduces the Factual Errors in LLM Responses

2024 · arXiv (Cornell University)

Mitigating hallucination issues is a key challenge that must be overcome to reliably deploy large language models (LLMs) in real-world scenarios. Recently, various methods have been proposed to detect and revise factual errors in LLM-generated …

Effects of Time Intervals and Semantic Weight on Action Fluency Tasks in Older Adults

2024 · Eon'eo cheong'gag jang'ae yeon'gu/Communication sciences & disorders

Objectives: The purpose of this study was to investigate the differences in performance of action fluency tasks (AFT) based on time intervals and the semantic weight of verbs among groups of healthy young and older …