8 papers
Quantum computer architecture with ions in tweezer arrays
Benjamin F. Schiffer, Christopher Monroe, Peter Zoller +1
We propose a quantum computer architecture based on ions confined in optical tweezer arrays, combining the long coherence times of trapped-ion qubits with the reconfigurability and…
AI Alignment From Social Choice Perspectives
Daniel Halpern, Evi Micha, Ariel D. Procaccia +3
Alignment from human feedback uses human judgments about model outputs to steer the behavior of language models after pretraining. When those judgments reflect conflicting views of…
Finding Common Ground in a Sea of Alternatives
Jay Chooi, Paul Gölz, Ariel D. Procaccia +2
We study the problem of selecting a statement that finds common ground across diverse population preferences. Generative AI is uniquely suited for this task because it can access a…
Metritocracy: Representative Metrics for Lite Benchmarks
Ariel Procaccia, Benjamin Schiffer, Serena Wang +1
A common problem in LLM evaluation is how to choose a subset of metrics from a full suite of possible metrics. Subset selection is usually done for efficiency or interpretability r…
Clone-Robust AI Alignment
Ariel D. Procaccia, Benjamin Schiffer, Shirley Zhang
A key challenge in training Large Language Models (LLMs) is properly aligning them with human preferences. Reinforcement Learning with Human Feedback (RLHF) uses pairwise compariso…
Improved Regret Bounds for Online Fair Division with Bandit Learning
Benjamin Schiffer, Shirley Zhang
We study online fair division when there are a finite number of item types and the player values for the items are drawn randomly from distributions with unknown means. In this set…