Zhaowei Wang

E-mail: zwanggy # cse dot ust dot hk

2021_Aug.jpg

Hi, I’m Zhaowei Wang (Chinese: 王昭为), also known as James. I’m currently a visiting scholar at Edinburgh NLP, working with Prof. Mark Steedman. I’m pursuing my PhD in the Department of CSE at HKUST, supervised by Prof. Yangqiu Song. I received my MPhil degree in the Department in CSE from HKUST in August 2023.



My research interests span a variety of tasks about reasoning, including planning, causal inference, abstraction, code for reasoning, and embodied AI. Primarily, I use cognitive approaches to build reasoning systems based on LLMs. I am fortunate to collaborate closely with Dr. Hongming Zhang at Tencent AI Lab, Seattle.

Research Highlights by Topic

Abstraction Knowledge
  1. arXiv
    Concept-Reversed Winograd Schema Challenge: Evaluating and Improving Robust Reasoning in Large Language Models via Abstraction
    Kaiqiao Han, Tianqing Fang, Zhaowei Wang, Yangqiu Song, and Mark Steedman
  2. ACL
    AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation Tuning with Plausibility Estimation
    Zhaowei Wang, Wei Fan, Qing Zong, Hongming Zhang, Sehyun Choi, Tianqing Fang, Xin Liu, Yangqiu Song, Ginny Y. Wong, and Simon See
    In The 62nd (2024) Annual Meeting of the Association for Computational Linguistics
  3. NAACL
    AbsPyramid: Benchmarking the Abstraction Ability of Language Models with a Unified Entailment Graph
    Zhaowei Wang, Haochen Shi, Weiqi Wang, Tianqing Fang, Hongming Zhang, Sehyun Choi, Xin Liu, and Yangqiu Song
    In Findings of 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Discourse Relations:
Planning using Rejection Sampling
  1. EMNLP
    SubeventWriter: Iterative Sub-event Sequence Generation with Coherence Controller
    Zhaowei Wang, Hongming Zhang, Tianqing Fang, Yangqiu Song, Ginny Y. Wong, and Simon See
    In 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP) (*oral)
Causal Inference
  1. ACL
    COLA: Contextualized Commonsense Causal Reasoning from the Causal Inference Perspective
    Zhaowei Wang, Quyet V. Do, Hongming Zhang, Jiayao Zhang, Weiqi Wang, Tianqing Fang, Yangqiu Song, Ginny Y. Wong, and Simon See
    In 2023 Annual Meeting of the Association for Computational Linguistics (ACL) (*oral)
Embodied AI:
  1. arXiv
    DivScene: Benchmarking LVLMs for Object Navigation with Diverse Scenes and Objects
    Zhaowei Wang, Hongming Zhang, Tianqing Fang, Ye Tian, Yue Yang, Kaixin Ma, Xiaoman Pan, Yangqiu Song, and Dong Yu

News

Jun 1, 2024 Two paper about abstraction and conceptualization are accepted by ACL2024.
Mar 13, 2024 A paper about implementing K-Line Theory for abstraction is accepted to NAACL 2024.
Mar 13, 2024 A paper about temporal relation bias is accepted to NAACL 2024.
Jan 18, 2024 A paper about enhancing LLMs’ commonsense reasoning ability is accepted to EACL 2024.
Oct 8, 2023 Two papers about detecting hallucination and commonsense denoising were accepted to EMNLP 2023.
Oct 4, 2023 Two papers about argument mining and sign language translation were accepted to Workshops at EMNLP 2023.
Aug 3, 2023 Our system of multi-modal argument mining obtains the first place in ImageArg-Shared-Task-2023@The 10th Workshop on Argument Mining at EMNLP 2023!
May 2, 2023 One paper about commonsense causal reasoning was accepted to ACL 2023.

Selected Awards

HKUST RedBird PhD Award 2023-2024

Hong Kong PhD Fellowship 2023

National Scholarship 2018-2019

National Scholarship 2017-2018

Merit Student in Heilongjiang Province 2017-2018

National Scholarship 2016-2017

Service

Area Chair: ACL ARR 2024 Apr, June, Aug, Oct

Conference Reviewer: ACL 2023, 2024; EMNLP 2022, 2023; NeurIPS 2024; ICLR 2025; NAACL 2024; KDD 2023; CIKM 2023; AAAI 2024; ACL ARR 2023 (all rounds); ACL ARR 2024 Feb, Apr; COLM 2024; EACL 2023, 2024; COLING 2022, 2025; LREC-COLING 2024; SDM 2023; AACL 2022, 2023; AKBC 2022; WiNLP@EMNLP 2024

External Journal Reviewer: JAIR 2023 Apr