Haochen Li's Homepage

alt text 

Ph.D Student
College of Computing and Data Science
Nanyang Technological University, Singapore
E-mail: haochen003 [AT] e.ntu.edu.sg
[GitHub] [Twitter] [Google Scholar]

About me

I am now a third-year Ph.D student, advised by Prof. Chunyan Miao. I received my B.Eng. degree in Electrical Engineering and B.A. degree in Economics in July 2021.

My research aims at bridging programming language and natural language. Specifically, I focus on code search (code retrieval) [EMNLP’22, EMNLP’23], code generation, and the synergy of the two through Generation-Augmented Retrieval [ACL’24] and Retrieval-Augmented Generation framework.

Publications

Preprints

  1. Towards Goal-oriented Prompt Engineering for Large Language Models: A Survey
    Haochen Li, Jonathan Leung, and Zhiqi Shen
    Arxiv, 2024. [paper] [resource]

Conferences and Journals

  1. SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages
    Holy Lovenia, …, Haochen Li, …, Zheng-Xin Yong, and Samuel Cahyawijaya
    In The 2024 Conference on Empirical Methods in Natural Language Processing. (EMNLP 2024)
    [paper] [website]

  2. Rewriting the Code: A Simple Method for Large Language Model Augmented Code Search
    Haochen Li, Xin Zhou, and Zhiqi Shen
    In The 62nd Annual Meeting of the Association for Computational Linguistics. (ACL 2024 Oral)
    [paper] [code]

  3. Rethinking Negative Pairs in Code Search
    Haochen Li, Xin Zhou, Luu Anh Tuan, and Chunyan Miao
    In The 2023 Conference on Empirical Methods in Natural Language Processing. (EMNLP 2023)
    [paper] [code]

  4. Exploring Representation-level Augmentation for Code Search
    Haochen Li, Chunyan Miao, Cyril Leung, Yanxian Huang, Yuan Huang, Hongyu Zhang, and Yanlin Wang
    In The 2022 Conference on Empirical Methods in Natural Language Processing. (EMNLP 2022)
    [paper] [code]

Experiences

Professional services

Conference Reviewer / PC Members: