About me

I am a Research Assistant working with professor Bryan Hooi at National University of Singapore, where I recently graduated with a bachelor's degree in Computer Science and Mathematics. I am also currently working with professor Hannaneh Hajishirzi and her student Zeqiu Wu at University of Washington.

My research is concentrated on Natural Language Processing (NLP). A more specific area that I am keen to explore is extending the usage of language models to more general settings.

Previously, I was advised by professor Tat Seng Chua and professor Lizi Liao at NExT++ Research Center. I worked on Conversation Disentanglement and Multi-party Response Generation to enable chit-chat agents to converse properly in multi-party dialogues that involve more than 2 speakers. Solving these tasks is crucial for the eventual application of chatbots in group chat and forums, where different topics may be discussed in a simultaneous and interleaved manner.

My current research directions include
• Applying LMs to multi-party settings: In multi-party settings, potentially with preset goals, different agents can assume different personas and roles, and the relations between the agents can be collaborative, adversarial, or competitive. There have been exciting works released recently that make use of multiple dialogue agents for settings such as problem-solving and text adventures. Exploration is needed for more complicated scenarios.

• Reasoning: I am exploring various ways to enhance the reasoning ability of LMs, including (1) collaboration between agents to make the reasoning path more logical and (2) augmentation of external knowledge to increase truthfulness and provide attribution.

Aside from these, I am excited to explore other NLP topics too.

Previous Research Topics

CV

Please see the attached document for more details.

Publications

  • Chengyu Huang, Zheng Zhang, Hao Fei, and Lizi Liao

    EMNLP

    Conversation Disentanglement with Bi-Level Contrastive Learning

    We propose to formulate Conversation Disentanglement as a global clustering task, in contrast to how it is traditionally solved as a pointing task. We use contrastive learning to pull embeddings of utterances from the same session closer and pull away those from different sessions. K means is then used to cluster the utterances.

    [Paper] [Slides]

  • Chengyu Huang, Zeqiu Wu, Yushi Hu, and Wenya Wang

    ACL, submitted

    Training Language Models to Generate Text with Citations via Fine-grained Rewards

    We propose to use fine-grained rewards to train LLMs to generate both supportive and relevant citations in the response, while preserving other qualities, such as answering correctness in the Question Anwering task.

    [Paper]

  • Yuexin Li, Chengyu Huang, Shumin Deng, Mei Lin Lock, Tri Cao, Nay Oo, Hoon Wei Lim, Bryan Hooi

    USENIX, submitted

    KnowPhish: Large Language Models Meet Multimodal Knowledge Graphs for Enhancing Reference-Based Phishing Detection

    We propose to construct an industry-based, multimodal knowledge base construction pipeline that are robust to temporal shift as well as a multimodal phishing detector that leverages HTML text to detect brand and credential-taking intentions.

    [Paper]

Projects

  • orizon

    Helping Large Language Models Generate Better Citations with Fine-Grained Rewards

    Supervisor: Professor Hannaneh Hajishirzi, Professor Wenya Wang, Dr Zeqiu Wu

    We observed that most existing LLMs do not output attributions for the claims they generated, while attributions can effectively reduce hallucination and increase model responses' explanability.

    We propose to use fine-grained rewards to train LLMs to both generate supportive and relevant citations, while preserving other qualities, such as answering correctness in the Question Anwering task.

    Toolstack: Python, PyTorch

    [Paper]

  • orizon

    Unleashing the Power of Reference-Based Phishing Detectors with Multimodal Knowledge Graphs

    Supervisor: Professor Bryan Hooi

    We observed that existing phishing detection methods are vulnerable to the temporal distributional shift of phishing webpages, and cannot generalize well when webpages shift their phishing intention from logos to HTML text.

    We propose to construct an industry-based, multimodal knowledge base construction pipeline that are robust to temporal shift as well as a multimodal phishing detector that leverages HTML text to detect brand and credential-taking intentions.

    Toolstack: Python, PyTorch

    [Paper]

  • orizon

    Multi-party Response Generation with Conversation Disentanglement

    Supervisor: Professor Tat Seng Chua, Professor Lizi Liao

    This work aims to provide a standard solution for multi-party response generation, and eventually enable dialogue agents to converse properly in multi-party conversations. There has been initial exploration on this task. However, the reliance of existing models on dialogue structure labels restricts their usefulness.

    A natural and more robust solution is to first disentangle the conversation, so that the context can be filtered and reorganized for response generation. While there has been substantial work that focuses on conversation disentanglement and response generation as standalone tasks, very few has explored the option of combining them together.

    To achieve the goal, we consider 2 integration options.

    • Integration with hard disentanglement: Directly filter the dialogue context with a disentanglement model and then input the resulting dialogue into a response generation system, pointing to this project and this project
    • Integration with soft disentanglement: Use a soft Relational Disentanglement to infer a relation graph and get the distilled context embedding, and then input the embedding into a decoder for response generation, pointing to this project and this project

    We evaluate both types of pipelines against the existing methods, and demonstrate their effectivness.

    Toolstack: Python, PyTorch

    [Honour Year Project Thesis]

  • orizon

    Disentangle Multi-party Conversations as Reordering with Curriculum [Hard Disentanglement]

    Supervisor: Professor Tat Seng Chua, Professor Lizi Liao

    We observed existing conversation disentanglement models' heavy reliance on handcrafted features and their dependence on Ubuntu IRC. This necessaites the development of a more generalizable techniques that can make the model disentangle as effectively in other settings.

    We propose to use reordering as a generalizable strategy to make conversation disentanglement more effective. Reordering has 2 roles. In training, it is used to generate new dialogues and augment the dataset. In inference, it is used recursively to correct the model's prediction.

    Toolstack: Python, PyTorch

    [Paper]

  • orizon

    Multi-party Response Generation with Relation Disentanglement [Soft Disentanglement]

    Supervisor: Professor Tat Seng Chua, Professor Lizi Liao

    While there have been works on multi-party response generation, they mostly require the dialogue structure ground truth to be given in advance, which undermines their usefulness when such ground truth is not present.

    As a continuation of the previous work, in this project, we investigate how to automatically infer the relations via relational thinking on subtle clues inside the conversation context without any human label, and leverage these relations to guide the neural response generation.

    Toolstack: Python, PyTorch

    [Paper]

  • orizon

    Conversation Disentanglement with Bi-Level Contrastive Learning [Hard Disentanglement]

    Supervisor: Professor Tat Seng Chua, Professor Lizi Liao

    We observed that many existing conversation disentanglement models do not pay sufficient attention to the dialogue context, while context is crucial in cases where the query utterance is ambiguous but the surrounding utterances indicate its belonging.

    We propose to formulate Conversation Disentanglement as a global clustering task, in contrast to how it is traditionally solved as a pointing task. We use contrastive learning to pull embeddings of utterances from the same session closer and pull away those from different sessions. K means is then used to cluster the utterances.

    Toolstack: Python, PyTorch

    [Paper] [Slides]

  • orizon

    Relational Thinking-based Response Generation [Soft Disentanglement]

    Supervisor: Professor Tat Seng Chua, Professor Lizi Liao

    Relational Thinking is a process where people spontaneously perceive complex relationships among objects or concepts. It was originated and developed in cognitive neuroscience and has remained under-explored in the NLP community.

    In this project, we work on the task of multi-party response generation, and we make use of Relational Thinking to infer a reply-to relation graph to filter the context in a multi-party conversation. This context is then used by the decoder for effective response generation.

    Toolstack: Python, PyTorch

    [Paper]

  • finance

    Bank Code Center

    I developed a service to store bank records for the Global Payment team in ByteDance. Its functionalities include

    • Submission of bank record CRUD requests through the user interface for internal enginners, capable of batch submission
    • Audition and execution of the CRUD requests
    • Cached reading of bank records from real time transcations

    Toolstack: Go, Kite, MongoDB

  • orizon

    RepoSense

    RepoSense is an open source contribution analysis tool for Git repositories. It is particularly useful for those who want a chronological visualisation of the code contributions and commits made to a group of repositories.

    As a project developer and mentor, I personally

    • Implemented highlighting of selected single entry or merged group on the summary panel
    • Implemented binary file support in authorship contribution panel
    • Wrote developer tutorial and release guide for RepoSense
    • Reviewed close to 100 pull requests and made 5 product releases

    Toolstack: JavaScript, Vue, Java

    [Product Site] [Repository]

  • orizon

    Transcation monitoring bot

    I developed a monitoring bot to monitor the customer transcations for the Global Payment team in ByteDance. It is capable of

    • Receiving alerts from an internal platform that monitors a Time Series Database (TSDB) storeing metrics emitted by the payment system
    • Sending messages to engineers in charge and help them handle the alerts
    • CRUD of alert trigger rules that are used by the internal monitoring platform

    Toolstack: Go, Ginex, Kite, MongoDB, Lark Open Platform

  • orizon

    UWave Mobile Application

    UWave is a mobile application that has more than 10000 users on campus. It provides various utilities to help people on campus connect with each other, learn about campus life, and manage their studies.

    I collaborated with other members in the development team of UWave and

    • Implemented part of the module calendar page
    • Implemented features on several other pages such as the but timing page, library access page, community page, and settings page
    • Supported its user growth especially in the NUS community

    Toolstack: Dart, Flutter

    [Android] [IOS]

Teaching

Teaching Activities

  1. CS3230, Design and Analysis of Algorithms, NUS

     Aug 2021 — Nov 2021

    Conduct weekly tutorials and consultation sessions; Serve as proctor; Mark the assignments and submissions

  2. CS2100, Computer Organization, NUS

     Jan 2021 — April 2021

    Conduct weekly lab sessions; Mark the lab reports

  3. CS1231S, Discrete Structures, NUS

     Aug 2020 - Nov 2020

    Conduct weekly tutorials and consultation sessions; Serve as proctor; Mark the assignments and submissions

  4. CS1101S, Programming Methodology, NUS

     Aug 2020 - Nov 2020

    Conduct weekly tutorials and consultation sessions; Mark the assignments

Awards

Honors and Awards

  1. IMDA Exellence in Computing Price

     5 June 2023

    A cash prize of $3500 awarded to the Most Outstanding Graduate in the Bachelor of Computing programme from the Infocomm Media Development Authority in Singapore; Awarded to 1/759 student in School of Computing

  2. Dean's List, School of Computing

    Jan - May 2023; Jan - May 2021; Aug - Dec 2020

    Awarded to the top 5 percent of students in the cohort in School of Computing in the corresponding semester

  3. Senior Middle 2 Scholarship

    Aug 2018 - May 2023

    A 5-year scholarship that covers the tuition and living costs of the 1-year bridging course and 4-year undergraduate study in Singapore