Publications

A collection of my research work.

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics · 2026

Defenses Against Prompt Attacks Learn Surface Heuristics

Shawn Li†, Chenxiao Yu†, Zhiyu Ni†, Hao Li, Charith Peris, Chaowei Xiao, Yue Zhao

Current defenses against prompt injection attacks rely on surface-level heuristics rather than robust understanding of attack patterns.

Paper

Proceedings of the 43rd International Conference on Machine Learning · 2026

Someone Hid It": Query-Agnostic Black-Box Attacks on LLM-Based Retrieval

Jiate Li, Defu Cao, Li Li, Wei Yang, Yuehan Qin, Chenxiao Yu, Tiannuo Yang, Ryan A. Rossi, Yan Liu, Xiyang Hu, Yue Zhao

A query-agnostic black-box attack framework that manipulates LLM-based retrieval systems without knowledge of user queries.

Paper

Findings of the Association for Computational Linguistics: ACL 2026 · 2026

Value-Action Alignment in Large Language Models under Privacy-Prosocial Conflict

Guanyu Chen, Chenxiao Yu, Xiyang Hu

Measuring whether LLMs' stated privacy and prosocial values predict their actual data-sharing actions.

Paper

arXiv Preprint · 2026

FORTIS: Benchmarking Over-Privilege in Agent Skills

Shawn Li, Chenxiao Yu, Han Wang, Wei Yang, Ryan Rossi, Franck Dernoncourt, Xiyang Hu, Philip Yu, Chaowei Xiao, Huan Zhang, Yue Zhao

A benchmark for measuring over-privilege in LLM agent skills and its security implications.

Paper

arXiv Preprint · 2026

De-conflating Preference and Qualification: Constrained Dual-Perspective Reasoning for Job Recommendation with Large Language Models

Bryce Kan, Wei Yang, Emily Nguyen, Ganghui Yi, Bowen Yi, Chenxiao Yu, Yan Liu

A constrained dual-perspective reasoning framework that separates preference from qualification in LLM-based job recommendation.

Paper

arXiv Preprint · 2026

Multimodal Generative Engine Optimization: Rank Manipulation for Vision-Language Model Rankers

Yixuan Du, Chenxiao Yu, Haoyan Xu, Ziyi Wang, Yue Zhao, Xiyang Hu

Jointly crafted imperceptible image perturbations and fluent textual suffixes manipulate vision-language model rankers.

Paper

arXiv Preprint · 2026

Tracing Moral Foundations in Large Language Models

Chenxiao Yu†, Bowen Yi†, Farzan Karimi-Malekabadi, Suhaib Abdurahman, Jinyi Ye, Shrikanth Narayanan, Yue Zhao, Morteza Dehghani

Do LLMs have human-like moral cognition?

Paper

Proceedings of the AAAI Conference on Artificial Intelligence · 2026

Mitigating Hallucinations in Large Language Models via Causal Reasoning

Yuangang Li, Yiqing Shen, Yi Nian, Jiechao Gao, Ziyi Wang, Chenxiao Yu, Shawn Li, Jie Wang, Xiyang Hu, Yue Zhao

A causal intervention framework that reduces hallucinations in LLMs by identifying and adjusting unstable internal pathways.

Paper

arXiv Preprint · 2025

Realistic Threat Perception Drives Intergroup Conflict: A Causal, Dynamic Analysis Using Generative-Agent Simulations

Suhaib Abdurahman, Farzan Karimi-Malekabadi, Chenxiao Yu, Nour S. Kteily, Morteza Dehghani

A causal analysis of how realistic threat perception drives intergroup conflict using generative-agent simulations.

Paper

arXiv Preprint · 2025

StealthRank: LLM Ranking Manipulation via Stealthy Prompt Optimization

Yiming Tang†, Yi Fan, Chenxiao Yu†, Tiankai Yang, Yue Zhao, Xiyang Hu

A framework that subtly manipulates LLM ranking outputs using optimized stealth prompts while evading detection.

Paper

arXiv Preprint · 2024

A Large-Scale Simulation on Large Language Models for Decision-Making in Political Science

Chenxiao Yu, Jinyi Ye, Yuangang Li, Zheng Li, Emilio Ferrara, Xiyang Hu, Yue Zhao

An extensive simulation study analyzing decision-making patterns of LLMs across identity conditions, threat cues, and moral scenarios.

Paper

arXiv Preprint · 2024

Political-LLM: Large Language Models in Political Science

Lincan Li, Jiaqi Li, Catherine Chen, Fred Gui, Hongjia Yang, Chenxiao Yu, Zhengguang Wang, Jianing Cai, Junlong Aaron Zhou, Bolin Shen, others

A large-scale evaluation of political reasoning, ideology prediction, and bias in modern LLMs using political science benchmarks.

Paper