Hi:wave:, I am Zhaoyi Li (Joey), a computer science PhD student under the collaboration program of University of Science and Technology of China (School of Computer Science and Technology and State Key Laboratory of Cognitive Intelligence, adviced by Prof.Defu Lian) and City University of Hong Kong (Department of Computer Science, co-adviced by Prof.Ying Wei and Prof.Linqi Song). The most fortunate thing for my early PhD life is that I met up with my brilliant professors! Previously, I got my Bachelor degree in Computer Science and Technology from University of Science and Technology of China in 2022, under the supervision of Prof.Cheng Li.

My ultimate research goal is to help with building trustworthy and transparent AI models. Specifically, I want to make human beings and neural network systems better understand each other (i.e., high interpretability and good generalization of blackbox deep models). I currently focus on investigating the compositionality of language models from the perspectives of generalization, reasoning pattern, implicit structure and so on, which is about the mechanism that language models decompose complex questions and concepts into primitive ones and re-compose them step-by-step to grasp the complex semantic meaning. In other words, I am curious about whether the end-to-end trained large-scale deep models are able to grok human-like reasoning skills or not and how to demonstrate it both empirically and theoretically. I would love to discuss on related topics should anyone is interested (always feel free to drop me an email: lizhaoyi777[AT]mail.ustc.edu.cn)!

🔥 News

  • 2024.09:  🎉🎉 One paper was accepted by Machine Learning Journal.
  • 2024.09:  🎉🎉 One paper was accepted by EMNLP’2024 (main conference).
  • 2024.05:  🎉🎉 Two papers were accepted by ACL’2024 (1$\times$main conference and 1$\times$findings).
  • 2023.05:  🎉🎉 One paper was accepted by ACL’2023 (main conference).

đź“ť Selected Publications

($*$ indicates the co-first authorship)

EMNLP 2024
sym

Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model Editing (EMNLP’2024)

Weichuan Wang$^*$, Zhaoyi Li$^*$, Defu Lian, Chen Ma, Linqi Song and Ying Wei

Paper Code

  • We investigate two common types of issues, Language Mismatch and Repetition, in LLM-based machine translation systems. We mitigate such issues to some extent by the refined model editing methods without hurting the general abilities of LLMs.
ACL 2024 Findings
sym

Understanding and Patching Compositional Reasoning in LLMs (ACL’2024 Findings)

Zhaoyi Li, Gangwei Jiang, Hong Xie, Linqi Song, Defu Lian and Ying Wei

Paper Code Blog(in Chinese)

  • We interpret the internal mechanism of compositional step-by-step reasoning on multi-hop factual knowledge inside large language models and propose a light-weight method based on model editing to patch their compositional reasoning errors.
ACL 2024
sym

Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation (ACL’2024)

Tianqi Zhong$^*$, Zhaoyi Li$^*$, Quan Wang, Linqi Song, Ying Wei, Defu Lian and Zhendong Mao

Paper Code

  • We propose CompMCTG, systematically unveiling the shortcoming of current multi-aspect controllable text generation methods on compositional generalization. Besides, we propose MetaMCTG, a meta-learning based training framework to improve the compositional generalization performance of current methods.
ACL 2023 Oral
sym

Learning to Substitute Spans towards Improving Compositional Generalization (ACL’2023 Oral)

Zhaoyi Li, Ying Wei and Defu Lian

Paper Code

  • We propose L2S2, a adversarial learning based text data augmentation scheme to improve the compositional generalization performance of neural sequence models (including LSTMs, Transformers and Pre-trained LMs).

🏆 Honors and Awards

  • 2024.10 China National Scholarship, USTC, Graduate Students.
  • 2022 ~ 2024 First prize, USTC Graduate Student Academic Scholarship.
  • 2022.06 Honored as The Outstanding Bachelor Graduate of USTC.
  • 2022.04 YuanQing (CEO of Lenovo Co.) Research Student Scholarship.
  • 2020 First prize, The 20th USTC RoboGame, Competition Group.
  • 2019 ~ 2022 First prize, USTC Excellent Undergraduate Scholarship.
  • 2019 USTC Ms.XIA Peisu Scholarship for Excellent Undergraduates of CS Major.
  • 2017.10 First prize, National (Senior) High School Mathematical Competition of China.
  • 2014.5 First prize, National (Junior) High School Mathematical Competition of China.

đź“– Educations

  • 2023.09 - now, PhD student, Department of Computer Science, City University of Hong Kong.
  • 2022.09 - now, PhD student, School of Computer Science and Technology, University of Science and Technology of China.
  • 2018.09 - 2022.07, Undergraduate, School of Computer Science and Technology, University of Science and Technology of China.

đź’» Internships

🎖 Services

🌷 Special Links

  • Here is the link to the homepage of my girlfriend: Ranran Shen.