I am a first-year PhD student at Northeastern University, advised by Prof. Weiyan Shi. I obtained my Master’s degree in Computer Science at UMass Amherst where I was lucky to work with Prof. Andrew McCallum and Prof. Hong Yu. I finished my undergraduate study in Computer Science at HKUST, where I was a research assistant at SMART lab working on medical image analysis with Professor Hao Chen and an NLP research intern at IDEA.

Research Interests. I am especially interested in label-efficient learning / weakly-supervised learning and improving the robustness and interpretability of neural networks. I am particularly enthusiastic about applying the implication to biology and medicine where labeled data are scarce and trustworthiness is valued.

I currently work on large language models, especially focusing on safety alignment and interpretation. I also have experience of knowledge distillation from LLMs and reasoning. I am also broadly interested in the memory view of LLMs.

Publications

2024

• Large Language Models are In-context Teachers for Knowledge Reasoning
  Jiachen Zhao, Zonghai Yao, Zhichao Yang, Hong Yu
  EMNLP 24 Findings.
  [pdf]

• Learning and Forgetting Unsafe Examples in Large Language Models
  Jiachen Zhao, Zhun Deng, David Madras, James Zou, Mengye Ren
  ICML 24.
  [pdf]

• Multistage Collaborative Knowledge Distillation from a Large Language Model for Semi-Supervised Sequence Generation
  Jiachen Zhao, Wenlong Zhao*, Andrew Drozdov*, Benjamin Rozonoyer, Md Arafat Sultan, Jay-Yoon Lee, Mohit Iyyer, Andrew McCallum
  ACL 24.
  [pdf]
  

• Adaptive Fusion of Deep Learning with Statistical Anatomical Knowledge for Robust Patella Segmentation from CT Images
  Jiachen Zhao, Tianshu Jiang, Yi Lin, Justin Chan, Ping-Keung Lewis Chan, Chunyi Wen, Hao Chen
  Journal of Biomedical & Health Informatics.
  [code] [pdf]
  

2023

• SELF-EXPLAIN: Teaching Large Language Models to Reason Complex Questions by Themselves
  Jiachen Zhao, Zonghai Yao, Zhichao Yang, Hong Yu
  Workshop on robustness of zero/few-shot learning in foundation models @ NIPS 23.
  [pdf]
  

• Student as an Inherent Denoiser of Noisy Teacher
  Jiachen Zhao
  3rd Workshop on Efficient Natural Language and Speech Processing @ NIPS 23.
  [pdf]
  

• In-Context Exemplars as Clues to Retrieving from Large Associative Memory
  Jiachen Zhao
  Neural Conversational AI @ ICML 23. Associative Memory & Hopfield Networks @ NIPS 23.
  [pdf]
  

2022

• Trigger-free Event Detection via Derangement Reading Comprehension
  Jiachen Zhao, Haiqin Yang
  arXiv.
  [pdf]