4 papers
Where's Waldo? Query-language Preference under Cross-lingual Knowledge Disparities
Dayeon Ki, Ruochen Zhang, Silviu Cucerzan +2
Large Language Models increasingly serve as interfaces for knowledge-intensive information seeking tasks across languages by synthesizing multilingual evidence. Prior work has show…
Reinforcing Agentic Creativity in Scientific Ideation with Night Science
Priyanka Kargupta, Silviu Cucerzan, Shweti Mahajan +4
Large language models (LLMs) excel at structured, verifiable tasks, but their low-entropy bias can produce homogeneous and predictable outputs, limiting their utility for open-ende…
Idea2Plan: Exploring AI-Powered Research Planning
Jin Huang, Silviu Cucerzan, Sujay Kumar Jauhar +1
Large language models (LLMs) have demonstrated significant potential to accelerate scientific discovery as valuable tools for analyzing data, generating hypotheses, and supporting…
Actions Speak Louder than Prompts: A Large-Scale Study of LLMs for Graph Inference
Ben Finkelshtein, Silviu Cucerzan, Sujay Kumar Jauhar +1
Large language models (LLMs) are increasingly used for text-rich graph machine learning tasks such as node classification in high-impact domains like fraud detection and recommenda…