Research

AI Alignment From Social Choice Perspectives

(α) Daniel Halpern, Evi Micha, Ariel D. Procaccia, Benjamin Schiffer, Itai Shapira, Shirley Zhang

SIGecom Exchanges

July 2026

How RLHF Amplifies Sycophancy

Itai Shapira, Gerdus Benadè, Ariel D. Procaccia

ICML 2026

Robust AI Evaluation through Maximal Lotteries

(r) Hadi Khalaf, Serena Lutong Wang^†, Daniel Halpern^†, Itai Shapira^†, Flavio P. Calmon, Ariel D. Procaccia

ICML 2026

Incentives in Federated Learning with Heterogeneous Agents

(α) Ariel D. Procaccia, Han Shao, Itai Shapira

ICLR 2026

Generative Social Choice

(α) Sara Fish, Paul Gölz, David C. Parkes, Ariel D. Procaccia, Gili Rusak, Itai Shapira, Manuel Wüthrich

Journal of the ACM

Extended version of the paper published at EC 2024

Pairwise Calibrated Rewards for Pluralistic Alignment

(α) Daniel Halpern, Evi Micha, Ariel D. Procaccia, Itai Shapira

NeurIPS 2025

SOAP: Improving and Stabilizing Shampoo using Adam

Nikhil Vyas^†, Depen Morwani^†, Rosie Zhao, Itai Shapira, David Brandfonbrener, Lucas Janson, Sham Kakade

ICLR 2025

A New Perspective on Shampoo’s Preconditioner

(r) Depen Morwani^†, Itai Shapira^†, Nikhil Vyas^†, Eran Malach, Sham M. Kakade, Lucas Janson

ICLR 2025

Bias Detection Via Signaling

(α) Yiling Chen, Tao Lin, Ariel D. Procaccia, Aaditya Ramdas, Itai Shapira

NeurIPS 2024

Optimal Engagement-Diversity Tradeoffs in Social Media

(α) Fabian Baumann, Daniel Halpern, Ariel D. Procaccia, Iyad Rahwan, Itai Shapira, Manuel Wüthrich

The ACM Web Conference (WWW) 2024