Jiali Cheng

Bio: I am a PhD student from UMass Lowell, advised by Prof. Hadi Amiri. Previously, I worked with Prof. Marinka Zitnik from Harvard University. Prior to that, I interned at THUNLP advised by Prof. Zhiyuan Liu and Dr. Yusheng Su.

I’ll be interning at Amazon Summer 2025.

Research: My research goal is to build Trustworthy and Efficient AI systems. My research interests span across multiple areas of AI

Trustworthy AI
- Bias & Fairness
- Adversarial Robustness
- Attack & Defense
- Machine Unlearning
- Interpretability
Tool Learning, expanding the abilities of AI models with external tools
AI4Science, leveraging AI tools to facilitate scientific discovery
Benchmark & Evaluation, designing novel benchmarks and evaluation protocols

news

May 01, 2025	🔥🔥ToolDelete is accepted to ICML 2025! This is the first work on unlearning tools from tool-augmented LLMs.
Apr 28, 2025	🔥🔥I was awarded the Computer Science Outstanding Graduate Research Award for Ph.D. Students at UMass Lowell! Many thanks to my advisor Prof. Amiri and collaborators!
Apr 01, 2025	🔥🔥Two preprints available: Exploring Mode Connectivity in the context of Unlearning, and Fair Graph Unlearning.
Jan 22, 2025	🔥🔥Two papers accepted to NAACL 2025! Main Conference (Short): EqualizeIR: Mitigating Linguistic Biases in Retrieval Models, and Workshop on Cognitive Modeling and Computational Linguistics (CMCL) Workshop: Linguistic Blind Spots of Large Language Models.
Oct 18, 2024	🔥🔥 MU-Bench is accepted to SafeGenAI @ NeurIPS’24! Stay tuned for code and leaderboard.
Sep 20, 2024	🔥🔥FairFlow is accepted to EMNLP 2024 Main! FairFlow effectively mitigates bias / spurious correlation for a wide range of NLU tasks.
Jul 01, 2024	🔥🔥MultiDelete is accepted by ECCV 2024.
Jun 25, 2024	🔥🔥New Preprint. MU-Bench, the first multitask multimodal comprehensive benchmark for Machine Unlearning.
Jun 01, 2024	🔥🔥1 paper accepted by ACL 2024 and 1 paper accepted by INTERSPEECH 2024.
Oct 01, 2023	🔥🔥1 paper accepted by EMNLP 2023.
Feb 01, 2023	New preprint on LLM and psychology. Check out the paper.
Jan 01, 2023	🔥🔥GNNDelete is accepted by ICLR 2023.

selected publications

Trustworthy

Tool Unlearning for Tool-Augmented LLMs

Jiali Cheng, and Hadi Amiri

In ICML , 2025

Bib

@inproceedings{cheng2025toom,
  title = {Tool Unlearning for Tool-Augmented LLMs},
  author = {Cheng, Jiali and Amiri, Hadi},
  year = {2025},
  booktitle = {ICML},
  url = {https://arxiv.org/abs/2502.01083}
}

Trustworthy

FairFlow: Mitigating Dataset Biases through Undecided Learning for Natural Language Understanding

Jiali Cheng, and Hadi Amiri

In EMNLP , 2024

Bib

@inproceedings{cheng-amiri-2024-fairflow,
  title = {FairFlow: Mitigating Dataset Biases through Undecided Learning for Natural Language Understanding},
  author = {Cheng, Jiali and Amiri, Hadi},
  year = {2024},
  booktitle = {EMNLP},
  url = {https://aclanthology.org/2024.emnlp-main.1225}
}

Trustworthy

MU-Bench: A multitask multimodal benchmark for machine unlearning

Jiali Cheng, and Hadi Amiri

In NeurIPS SafeGenAI Workshop , 2024

arXiv Bib

@inproceedings{cheng2024mu,
  title = {MU-Bench: A multitask multimodal benchmark for machine unlearning},
  author = {Cheng, Jiali and Amiri, Hadi},
  booktitle = {NeurIPS},
  year = {2024},
  url = {https://arxiv.org/abs/2406.14796}
}

Trustworthy

MultiDelete for Multimodal Machine Unlearning

Jiali Cheng, and Hadi Amiri

In ECCV , 2024

arXiv Bib

@inproceedings{cheng2024multidelete,
  title = {MultiDelete for Multimodal Machine Unlearning},
  author = {Cheng, Jiali and Amiri, Hadi},
  booktitle = {ECCV},
  year = {2024},
  url = {https://arxiv.org/abs/2311.12047}
}

Evaluation

Exploring the Impact of Model Scaling on Parameter-Efficient Tuning

Yusheng Su, Chi-Min Chan, Jiali Cheng, Yujia Qin, Yankai Lin, Shengding Hu, Zonghan Yang, Ning Ding , and 4 more authors

In EMNLP , 2023

arXiv Bib

@inproceedings{su-etal-2023-exploring,
  title = {Exploring the Impact of Model Scaling on Parameter-Efficient Tuning},
  author = {Su, Yusheng and Chan, Chi-Min and Cheng, Jiali and Qin, Yujia and Lin, Yankai and Hu, Shengding and Yang, Zonghan and Ding, Ning and Sun, Xingzhi and Xie, Guotong and Liu, Zhiyuan and Sun, Maosong},
  year = {2023},
  booktitle = {EMNLP},
  url = {https://aclanthology.org/2023.emnlp-main.931/}
}

Trustworthy

GNNDelete: A General Strategy for Unlearning in Graph Neural Networks

Jiali Cheng, George Dasoulas, Huan He, Chirag Agarwal, and Marinka Zitnik

In ICLR , 2023

arXiv Bib

@inproceedings{cheng2023gnndelete,
  title = {{GNND}elete: A General Strategy for Unlearning in Graph Neural Networks},
  author = {Cheng, Jiali and Dasoulas, George and He, Huan and Agarwal, Chirag and Zitnik, Marinka},
  booktitle = {ICLR},
  year = {2023},
  url = {https://arxiv.org/abs/2302.13406}
}