activity
20242026
collaborators

9 papers

cs.AI2026

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…

cs.LG2026

Robust AI Evaluation through Maximal Lotteries

Hadi Khalaf, Serena L. Wang, Daniel Halpern +3

The standard way to evaluate language models on subjective tasks is through pairwise comparisons: an annotator chooses the "better" of two responses to a prompt. Leaderboards aggre…

cs.AI2026

How RLHF Amplifies Sycophancy

Itai Shapira, Gerdus Benade, Ariel D. Procaccia

Large language models often exhibit increased sycophantic behavior after preference-based post-training, showing a stronger tendency to affirm a user's stated or implied belief eve…

cs.GT2026

Incentives in Federated Learning with Heterogeneous Agents

Ariel D. Procaccia, Han Shao, Itai Shapira

Federated learning promises significant sample-efficiency gains by pooling data across multiple agents, yet incentive misalignment is an obstacle: each update is costly to the cont…

cs.LG2025

Pairwise Calibrated Rewards for Pluralistic Alignment

Daniel Halpern, Evi Micha, Ariel D. Procaccia +1

Current alignment pipelines presume a single, universal notion of desirable behavior. However, human preferences often diverge across users, contexts, and cultures. As a result, di…

cs.GT2025

Generative Social Choice

Sara Fish, Paul Gölz, David C. Parkes +4

The mathematical study of voting, social choice theory, has traditionally only been applicable to choices among a few predetermined alternatives, but not to open-ended decisions su…