Experiences
21' - Now : AI Engineer @
24'.5 - 24'.8 : Research Intern @
23'.5 - 23'.8 : Research Intern @
22'.5 - 22'.8 : Research Intern @

Dong-Ho Lee (이동호)

PhD Candidate @ (dongho.lee[at]usc.edu)

I am pursuing a PhD in Computer Science with a specialization in ML/NLP at the University of Southern California, Information Science Institute. Under the guidance of Prof. Jay Pujara from the Knowledge Graph Center at ISI, and in collaboration with Prof. Xiang Ren, my research endeavors center around Natural Language Processing, Knowledge Graphs, and Machine Learning.

My primary objective is to develop robust forecasting systems that significantly influence decision-making and safety across various sectors. To realize this, I am exploring large language models (LLMs) in following directions:

  • LLM as general sequence modeler for statistical forecasting: Leveraging the in-context learning ability of LLM with historical data to model patterns in a zero-shot manner. [Paper 1]
  • LLM as world model for judgmental forecasting: Employing LLM to simulate human judgment in forecasting scenarios and applying those simulations.
  • Agent system: Building a helpful assistant for financial-decision making with [Product]

I'm currently working as a research intern at (2024 with Long Jin, Xinyang Yi and Adam Kraft), and I was a research intern at (2023 with Francesco Barbieri) and (2022 with Sujay Jauhar);
I am closely working with Sungjoon Park and Jihyung Moon at to build AI agent products (financial decision, medical coordinator).

News

  • [2024-02-15] I passed my qualifying exam and officially became a PhD Candidate.
  • [2023-12-07] I will serve as an Area Chair at NAACL 2024 (ARR October 2024).
  • [2023-10-30] I will serve as an Area Chair at EACL 2024 (ARR October 2023).
  • [2023-10-07] Three first-authored papers (Paper 1, Paper 2, Paper 3) have been accepted to EMNLP 2023!
  • [2023-05-08] XMD, Explanation-based model debugging framework, has been accepted to ACL 2023 Demo!
  • [2023-01-21] One first-authored paper (AutoTriggER) has been accepted to EACL 2023!
  • [2022-08-24] Invited talks on Explanation based Learning at POSTECH.
  • [2022-02-24] Two first-authored papers (Paper 1, Paper 2) have been accepted to ACL 2022!

Talks

  • Explanation-based Learning [link], 2022, Invited Talks @ POSTECH
  • Explanation-based Learning [link], 2022, Invited Talks @ Microsoft