5 papers
Welfare as a Guiding Principle for Machine Learning -- From Compass, to Lens, to Roadmap
Nir Rosenfeld, Haifeng Xu
Decades of research in machine learning have given us powerful tools for making accurate predictions. But when used in social settings and on human inputs, better accuracy does not…
The Keychain Problem: On Minimizing the Opportunity Cost of Uncertainty
Ramiro N. Deo-Campo Vuong, Robert Kleinberg, Aditya Prasad +2
In this paper, we introduce a family of sequential decision-making problems, collectively termed the Keychain Problem, that involve exploring a set of actions to maximize expected…
Tokenized Bandit for LLM Decoding and Alignment
Suho Shin, Chenghao Yang, Haifeng Xu +1
We introduce the tokenized linear bandit (TLB) and multi-armed bandit (TMAB), variants of linear and stochastic multi-armed bandit problems inspired by LLM decoding and alignment.…
Cer-Eval: Certifiable and Cost-Efficient Evaluation Framework for LLMs
Ganghua Wang, Zhaorun Chen, Bo Li +1
As foundation models continue to scale, the size of trained models grows exponentially, presenting significant challenges for their evaluation. Current evaluation practices involve…
Sample Complexity of Linear Regression Models for Opinion Formation in Networks
Haolin Liu, Rajmohan Rajaraman, Ravi Sundaram +3
Consider public health officials aiming to spread awareness about a new vaccine in a community interconnected by a social network. How can they distribute information with minimal…