Publications and Preprints

Google Scholar & Semantic Scholoar

Large Language Models

1. Measuring and Reducing LLM Hallucination without Gold-Standard Answers via Expertise-Weighting
   Jiaheng Wei, Yuanshun Yao, Jean-Francois Ton, Hongyi Guo, Andrew Estornell, Yang Liu
   (Under Review) [Category: LLM Evaluation; LLM Alignment; In-Context Learning; Supervised Fine-Tuning]

2. Human-Instruction-Free LLM Self-Alignment with Limited Samples
   Hongyi Guo, Yuanshun Yao, Wei Shen, Jiaheng Wei, Xiaoying Zhang, Zhaoran Wang, Yang Liu
   (Under Review) [paper] [Category: LLM Alignment; In-Context Learning]

Trustworthy Machine Learning

1. To Aggregate or Not? Learning with Separate Noisy Labels
   Jiaheng Wei*, Zhaowei Zhu*, Tianyi Luo, Ehsan Amid, Abhishek Kumar, Yang Liu
   KDD – ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023
   [paper] [Category: Label Noise]

2. Distributionally Robust Post-hoc Clasifiers under Prior Shifts
   Jiaheng Wei, Harikrishna Narasimhan, Ehsan Amid, Wensheng Chu, Yang Liu, Abhishek Kumar
   ICLR – International Conference on Learning Representations, 2023
   [paper] [code] [Category: Long-Tailed Learning, Group-Dro]

3. To Smooth or Not? When Label Smoothing Meets Noisy Labels
   Jiaheng Wei, Hangyu Liu, Tongliang Liu, Gang Niu, Masashi Sugiyama, Yang Liu
   ICML (Long Presentation) – International Conference on Machine Learning, 2022
   [paper] [code] [Category: Label Noise]

4. Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations
   Jiaheng Wei*, Zhaowei Zhu*, Hao Cheng, Tongliang Liu, Gang Niu, Yang Liu
   ICLR – International Conference on Learning Representations, 2022
   [paper] [data] [code] [Category: Label Noise]

5. When Optimizing f-divergence is Robust with Label Noise
   Jiaheng Wei and Yang Liu
   ICLR – International Conference on Learning Representations, 2021
   [paper] [code] [Category: Label Noise]

6. Fairness Improve Learning from Noisily Labeled Long-Tailed Data
   Jiaheng Wei, Zhaowei Zhu, Gang Niu, Tongliang Liu, Sijia Liu, Masashi Sugiyama, Yang Liu
   (Under Review) [paper] [Category: Long-Tailed Learning]

7. Do humans and machines have the same eyes? Human-machine perceptual differences on image classification.
   Minghao Liu, Jiaheng Wei, Yang Liu, James Davis
   (Under Review) [paper] [Category: Human-in-the-loop]

Incentives in Machine Learning

1. Sample Elicitation
   Jiaheng Wei*, Zuyue Fu*, Yang Liu, Xingyu Li, Zhuoran Yang, Zhaoran Wang
   AISTATS – International Conference on Artificial Intelligence and Statistics, 2021
   [paper] [code] [Category: Information Elicitation]

2. Auditing for Federated Learning: A Model Elicitation Approach
   Yang Liu, Rixing Lou, Jiaheng Wei [Alphabetical order] DAI – Distributed AI, 2023
   [paper] [Category: Information Elicitation]

3. Incentives for Federated Learning: a Hypothesis Elicitation Approach
   Yang Liu, Jiaheng Wei
   ICML workshop – Workshop on Incentives in Machine Learning, 2020
   [paper] [Category: Information Elicitation]

4. Beyond Data Sharing: Incentivizing Heterogeneous Clients in Strategic Federated Learning
   Jinlong Pang, Jiaheng Wei, Chen Qian, Yang Liu
   (Under Review) [Category: Information Elicitation]

Other Papers

1. DuelGAN: A Duel between Two Discriminators Stabilizes the GAN Training
   Jiaheng Wei*, Minghao Liu*, Jiahao Luo, Andrew Zhu, James Davis, Yang Liu
   ECCV – European Conference on Computer Vision, 2022
   [paper] [code] [Category: Deep Generative Models]

2. Consensus on Dynamic Stochastic Block Models: Fast Convergence and Phase Transitions
   Haoyu Wang, Jiaheng Wei, Zhenyuan Zhang
   (Under Review) [paper] [Category: Majority Dynamics]

(*: denotes equal contributions)