7 papers
Automating and Scaling Behavioral Scientific Research on AI Agents
Soo Yong Lee, Jongha Lee, Jaewan Chun +7
As AI agents are increasingly deployed in complex environments, understanding their behaviors becomes critical. Yet behavioral scientific research on AI agents remains manual and l…
Improving Rare Medication Recommendation with Counterfactual Data Augmentation and Large Language Models
Shinhwan Kang, Soo Yong Lee, Jaewon Kim +2
AI-based medication recommendation systems have attracted substantial attention due to their potential to enhance patient safety and therapeutic outcomes. Despite the clinical impo…
Feature-Centric Unsupervised Node Representation Learning Without Homophily Assumption
Sunwoo Kim, Soo Yong Lee, Kyungho Kim +3
Unsupervised node representation learning aims to obtain meaningful node embeddings without relying on node labels. To achieve this, graph convolution, which aggregates information…
Emergence of psychopathological computations in large language models
Soo Yong Lee, Hyunjin Hwang, Taekwan Kim +5
Can large language models (LLMs) instantiate computations of psychopathology? An effective approach to the question hinges on addressing two factors. First, for conceptual validity…
'Hello, World!': Making GNNs Talk with LLMs
Sunwoo Kim, Soo Yong Lee, Jaemin Yoo +1
While graph neural networks (GNNs) have shown remarkable performance across diverse graph-related tasks, their high-dimensional hidden representations render them black boxes. In t…
On Measuring Unnoticeability of Graph Adversarial Attacks: Observations, New Measure, and Applications
Hyeonsoo Jo, Hyunjin Hwang, Fanchen Bu +3
Adversarial attacks are allegedly unnoticeable. Prior studies have designed attack noticeability measures on graphs, primarily using statistical tests to compare the topology of or…