Shengwei Xu

Shengwei Xu

Incoming Googler

Posts by Collection

portfolio

publications

SURPRISE! and When to Schedule It

Published in Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI 2021), 2021

A study of when to schedule surprise-maximizing outcomes in multi-round competitions.

Recommended citation: Zhihuan Huang, Shengwei Xu, You Shan, Yuxuan Lu, Yuqing Kong, Tracy Xiao Liu, and Grant Schoenebeck. (2021). "SURPRISE! and When to Schedule It." Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI 2021).
Download Paper

BONUS! Maximizing Surprise

Published in Proceedings of the ACM Web Conference 2022 (WWW 2022), 2022

An analysis of optimal bonus sizing in multi-round competitions to maximize expected audience surprise.

Recommended citation: Zhihuan Huang, Yuqing Kong, Tracy Xiao Liu, Grant Schoenebeck, and Shengwei Xu. (2022). "BONUS! Maximizing Surprise." Proceedings of the ACM Web Conference 2022 (WWW 2022).
Download Paper

Spot Check Equivalence: An Interpretable Metric for Information Elicitation Mechanisms

Published in Proceedings of the ACM Web Conference 2024 (WWW 2024), 2024

An interpretable metric connecting spot-checking and peer prediction mechanisms for information elicitation.

Recommended citation: Shengwei Xu, Yichi Zhang, Paul Resnick, and Grant Schoenebeck. (2024). "Spot Check Equivalence: An Interpretable Metric for Information Elicitation Mechanisms." Proceedings of the ACM Web Conference 2024 (WWW 2024).
Download Paper

Eliciting Informative Text Evaluations with Large Language Models

Published in Proceedings of the 25th ACM Conference on Economics and Computation (EC 2024), 2024

Peer prediction mechanisms for motivating informative text feedback using Large Language Models as predictors.

Recommended citation: Yuxuan Lu, Shengwei Xu, Yichi Zhang, Yuqing Kong, and Grant Schoenebeck. (2024). "Eliciting Informative Text Evaluations with Large Language Models." Proceedings of the 25th ACM Conference on Economics and Computation (EC 2024).
Download Paper

Benchmarking LLMs’ Judgments with No Gold Standard

Published in Proceedings of the Thirteenth International Conference on Learning Representations (ICLR 2025), 2025

A benchmark and metric for evaluating LLM judgments in settings without a gold-standard reference.

Recommended citation: Shengwei Xu, Yuxuan Lu, Grant Schoenebeck, and Yuqing Kong. (2025). "Benchmarking LLMs' Judgments with No Gold Standard." Proceedings of the Thirteenth International Conference on Learning Representations (ICLR 2025).
Download Paper

Stochastically Dominant Peer Prediction

Published in Advances in Neural Information Processing Systems (NeurIPS 2025), 2025

A stronger peer prediction guarantee that incentivizes truthful reporting for broad classes of monotone utility functions.

Recommended citation: Yichi Zhang, Shengwei Xu, David Pennock, and Grant Schoenebeck. (2025). "Stochastically Dominant Peer Prediction." Advances in Neural Information Processing Systems (NeurIPS 2025).
Download Paper

Ad Insertion in LLM-Generated Responses

Published in Workshop on Frontiers of Online Advertising at the 26th ACM Conference on Economics and Computation (EC 2025), 2025

A framework for inserting ads into LLM-generated responses while preserving contextual coherence, efficiency, privacy, and explicit disclosure.

Recommended citation: Shengwei Xu, Zhaohua Chen, Xiaotie Deng, Zhiyi Huang, and Grant Schoenebeck. (2025). "Ad Insertion in LLM-Generated Responses." Workshop on Frontiers of Online Advertising at the 26th ACM Conference on Economics and Computation (EC 2025).
Download Paper

talks

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.