12 papers
Escaping the Mode Lottery: Multi-Response Training Improves Language Model Generalization
Hasan Amin, Kian Ahrabian, Ming Yin +1
Modern language-model fine-tuning typically pairs each prompt with a single response, even though many prompts admit multiple valid completions. This effectively reduces a multi-mo…
From Fallback to Frontline: When Can LLMs be Superior Annotators of Human Perspectives?
Hasan Amin, Harry Yizhou Tian, Xiaoni Duan +3
Although large language models (LLMs) are increasingly used as annotators at scale, they are typically treated as a pragmatic fallback rather than a faithful estimator of human per…
A Unified Stability Analysis of SAM vs SGD: Role of Data Coherence and Emergence of Simplicity Bias
Wei-Kai Chang, Rajiv Khanna
Understanding the dynamics of optimization in deep learning is increasingly important as models scale. While stochastic gradient descent (SGD) and its variants reliably find soluti…
Sharpness-Aware Machine Unlearning
Haoran Tang, Rajiv Khanna
We characterize the effectiveness of Sharpness-aware minimization (SAM) under machine unlearning scheme, where unlearning forget signals interferes with learning retain signals. Wh…
Align When They Want, Complement When They Need! Human-Centered Ensembles for Adaptive Human-AI Collaboration
Hasan Amin, Ming Yin, Rajiv Khanna
In human-AI decision making, designing AI that complements human expertise has been a natural strategy to enhance human-AI collaboration, yet it often comes at the cost of decrease…
Why Some Models Resist Unlearning: A Linear Stability Perspective
Wei-Kai Chang, Rajiv Khanna
Machine unlearning, the ability to erase the effect of specific training samples without retraining from scratch, is critical for privacy, regulation, and efficiency. However, most…