Short Bio

I am a senior research scientist in Google DeepMind working on natural language processing and data mining. My research aims to assist humans to better interact with AI systems for knowledge acquisition, decision making, and creative thinking.

I completed my Ph.D. at University of Illinois, Urbana-Champaign (UIUC), advised by Prof. Jiawei Han.

What's new!

May 2024 - Two papers about (1) Explanation-enhanced LLM In-context Learning, and (2) Text Preference Prediction are accepted in ACL 2024 (Main).

May 2024 - One paper on LLM Distillation is accepted in ACL 2024 (Findings).

May 2024 - One paper on Knowledge Distillation with Perturbed Loss is accepted in KDD 2024.

May 2024 - One paper on LLM-based Text Ranker is accepted in NAACL 2024.

Sept. 2023 - One paper on LLM-based Attributed Training Data Generation is accepted in NeurIPS 2023 Dataset and Benchmark Track.

June 2023 - One paper on Corpus-Based Relation Extraction is accepted in ECMLPKDD 2023.

May 2023 - Two papers about (1) local boosting for weakly supervised learning, and (2) unbiased learning to rank are accepted in KDD 2023.

Apr. 2023 - Three papers about LLMs are accepted in ACL 2023.

Apr. 2023 - One paper on Few-Shot Biomedical Knowledge Fusion is accepted in SIGIR 2023.

Mar. 2023 - One paper on Chain-of-Thought Prompt Understanding is accepted in ICLR 2023 (ME-FoMo Workshop).

Jan. 2023 - Two papers on Explanation-enhanced news headline hallucination detection and Unsupervised Event Chain Mining are accepted in WWW 2023.

Oct. 2022 - My book on Automated Taxonomy Discovery and Exploration is published in Springer Nature.

Oct. 2022 - Together with Dongha Lee, our work on Generation-based Topic Taxonomy Completion is accepted in EMNLP 2022 Findings.

Area of Interests

My primary areas of interests in research include:

  • Data Mining
  • Natural Language Processing
  • Machine Learning

I have also worked on:

  • Interactive Data Visualization
  • Data Wrangling
  • Web Development


Email mickeysjm[at]