Li, Jie

VisTR: Visualizations as Representations for Time-series Table Reasoning

2024 · arXiv (Cornell University)

Time-series table reasoning interprets temporal patterns and relationships in data to answer user queries. Despite recent advancements leveraging large language models (LLMs), existing methods often struggle with pattern recognition, context lost in long time-series data, …

Probing the Robustness of Large Language Models Safety to Latent Perturbations

2025 · arXiv (Cornell University)

Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We argue that …