5 papers
Chain-of-Influence: Tracing Interdependencies Across Time and Features in Clinical Predictive Modelings
Yubo Li, Rema Padman
Modeling clinical time-series data is hampered by the challenge of capturing latent, time-varying dependencies among features. State-of-the-art approaches often rely on black-box m…
Time-To-Inconsistency: A Survival Analysis of Large Language Model Robustness to Adversarial Attacks
Yubo Li, Ramayya Krishnan, Rema Padman
Large Language Models (LLMs) have revolutionized conversational AI, yet their robustness in extended multi-turn dialogues remains poorly understood. Existing evaluation frameworks…
Co-Alignment: Rethinking Alignment as Bidirectional Human-AI Cognitive Adaptation
Yubo Li, Weiyi Song
Current AI alignment through RLHF follows a single directional paradigm that AI conforms to human preferences while treating human cognition as fixed. We propose a shift to co-alig…
Firm or Fickle? Evaluating Large Language Models Consistency in Sequential Interactions
Yubo Li, Yidi Miao, Xueying Ding +2
Large Language Models (LLMs) have shown remarkable capabilities across various tasks, but their deployment in high-stake domains requires consistent and coherent behavior across mu…
No Black Box Anymore: Demystifying Clinical Predictive Modeling with Temporal-Feature Cross Attention Mechanism
Yubo Li, Xinyu Yao, Rema Padman
Despite the outstanding performance of deep learning models in clinical prediction tasks, explainability remains a significant challenge. Inspired by transformer architectures, we…