4 papers · 1 filter
Don't Walk the Line: Boundary Guidance for Filtered Generation
Sarah Ball, Andreas Haupt
Generative models are increasingly paired with safety classifiers that filter harmful or undesirable outputs. A common strategy is to fine-tune the generator to reduce the probabil…
Latent Adversarial Regularization for Offline Preference Optimization
Enyi Jiang, Yibo Jacky Zhang, Yinglun Xu +3
Learning from human feedback typically relies on preference optimization that constrains policy updates through token-level regularization. However, preference optimization for lan…
Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value
Joe Edelman, Tan Zhi-Xuan, Ryan Lowe +30
Beneficial societal outcomes cannot be guaranteed by aligning individual AI systems with the intentions of their operators or users. Even an AI system that is perfectly aligned to…
Position: Machine Learning Conferences Should Establish a "Refutations and Critiques" Track
Rylan Schaeffer, Joshua Kazdan, Yegor Denisov-Blanch +11
Science progresses by iteratively advancing and correcting humanity's understanding of the world. In machine learning (ML) research, rapid advancements have led to an explosion of…