Zhehao Zhang

			@inproceedings{jones2026benign,
  title={When benign inputs lead to severe harms: Eliciting unsafe unintended behaviors of computer-use agents},
  author={Jones, Jaylen and Zhang, Zhehao and Ning, Yuting and Fosler-Lussier, Eric and St-Charles, Pierre-Luc and Bengio, Yoshua and Song, Dawn and Su, Yu and Sun, Huan},
  booktitle={The 43rd International Conference on Machine Learning (ICML)},
  year={2026}
}
		

			@inproceedings{ning2026misact,
  title={When Actions Go Off-Task: Detecting and Correcting Misaligned Actions in Computer-Use Agents},
  author={Ning, Yuting and Jones, Jaylen and Zhang, Zhehao and Ye, Chentao and Ruan, Weitong and Li, Junyi and Gupta, Rahul and Sun, Huan},
  booktitle={The 43rd International Conference on Machine Learning (ICML)},
  year={2026}
}
		

			@inproceedings{zhang2025falsereject,
  title={Falsereject: A resource for improving contextual safety and mitigating over-refusals in llms via structured reasoning},
  author={Zhang, Zhehao and Xu, Weijie and Wu, Fanyou and Reddy, Chandan K},
  booktitle={Conference on Language Modeling (COLM)},
  year={2025}
}
		

			@inproceedings{NEURIPS2024_f5198bc2,
author = {Zhang, Zhehao and Chen, Jiaao and Yang, Diyi},
booktitle = {Advances in Neural Information Processing Systems},
editor = {A. Globerson and L. Mackey and D. Belgrave and A. Fan and U. Paquet and J. Tomczak and C. Zhang},
pages = {135904--135942},
publisher = {Curran Associates, Inc.},
title = {DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph},
url = {https://proceedings.neurips.cc/paper_files/paper/2024/file/f5198bc255e1d5f959edd6d1d1a86fab-Paper-Conference.pdf},
volume = {37},
year = {2024}
}
		

			@article{zhang2024vipact,
  title={VipAct: Visual-Perception Enhancement via Specialized VLM Agent Collaboration and Tool-use},
  author={Zhang, Zhehao and Rossi, Ryan A. and Yu, Tong and Dernoncourt, Franck and Zhang, Ruiyi and Gu, Jiuxiang and Kim, Sungchul and Chen, Xiang and Wang, Zichao and Lipka, Nedim},
  journal={arXiv preprint arXiv:2410.16400},
  year={2024}
}
		

			@inproceedings{zhang2024gpt4v,
  title={Is GPT-4V (ision) All You Need for Automating Academic Data Visualization? Exploring Vision-Language Models' Capability in Reproducing Academic Charts},
  author={Zhang, Zhehao and Ma, Weicheng and Vosoughi, Soroush},
  booktitle={Findings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  year={2024}
}
		

			@inproceedings{zhang2024e5,
  title={E5: Zero-shot Hierarchical Table Analysis using Augmented LLMs via Explain, Extract, Execute, Exhibit, and Extrapolate},
  author={Zhang, Zhehao and Gao, Yan and Lou, Jian-Guang},
  booktitle={Proceedings of the 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)},
  year={2024}
}
		

			@inproceedings{zhang2023crt,
  title={CRT-QA: A Dataset of Complex Reasoning Question Answering over Tabular Data},
  author={Zhang, Zhehao and Li, Xitao and Gao, Yan and Lou, Jian-Guang},
  booktitle={Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  year={2023}
}
		

			@inproceedings{zhang2023hate,
  title={Mitigating Biases in Hate Speech Detection from A Causal Perspective},
  author={Zhang, Zhehao and Chen, Jiaao and Yang, Diyi},
  booktitle={Findings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  year={2023}
}
		

			@article{zhang2024personalization,
  title={Personalization of Large Language Models: A Survey},
  author={Zhang, Zhehao and Rossi, Ryan A. and Kveton, Branislav and Shao, Yijia and Yang, Diyi and Zamani, Hamed and Dernoncourt, Franck and Barrow, Joe and Yu, Tong and Kim, Sungchul and Zhang, Ruiyi and Gu, Jiuxiang and Derr, Tyler and Chen, Hongjie and Wu, Junda and Chen, Xiang and Wang, Zichao and Mitra, Subrata and Lipka, Nedim and Ahmed, Nesreen and Wang, Yu},
  journal={arXiv preprint arXiv:2411.00027},
  year={2024}
}
		

			@article{ziems2023llm,
  title={Can Large Language Models Transform Computational Social Science?},
  author={Ziems, Caleb and Held, William and Shaikh, Omar and Chen, Jiaao and Zhang, Zhehao and Yang, Diyi},
  journal={Computational Linguistics},
  volume={50},
  number={1},
  pages={237--280},
  year={2023}
}
		

			@article{ning2026skillharm,
  title={SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction},
  author={Ning, Yuting and Zhang, Zhehao and Lal, Yash Kumar and Gou, Boyu and Li, Junyi and Ruan, Weitong and Ye, Chentao and Gupta, Rahul and Yang, Diyi and Su, Yu and others},
  journal={arXiv preprint arXiv:2606.02540},
  year={2026}
}
		

			@article{xie2026quest,
  title={QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks},
  author={Xie, Jian and Lin, Tianhe and Wang, Zilu and Ning, Yuting and Yao, Yuekun and Xue, Tianci and Zhang, Zhehao and Li, Zhongyang and Zhang, Kai and Wu, Yufan and others},
  journal={arXiv preprint arXiv:2605.24218},
  year={2026}
}
		

			@article{zhang2025distractor,
  title={Distractor Injection Attacks on Large Reasoning Models: Characterization and Defense},
  author={Zhang, Zhehao and Xu, Weijie and Cui, Shixian and Reddy, Chandan K},
  journal={arXiv preprint arXiv:2510.16259},
  year={2025}
}