About Me

I am currently a research scientist at the Language and Science AI Lab, Alibaba DAMO Academy. Prior to that, I obtained my Ph.D. degree from The Chinese University of Hong Kong, under the supervision of Prof. Wai Lam. My research mainly lies in Retrieval Augmented Generation (RAG), Data Augmentation, and Language Agent.

Education

  • Aug. 2020 - July 2024, Ph.D.
    Department of Systems Engineering and Engineering Management,
    The Chinese University of Hong Kong

  • Sep. 2015 - Jun. 2019, B.E.
    Computer Science from Yingcai Honors College,
    University of Electronic Science and Technology of China

Publications

  • Reasons to Reject? Aligning Language Models with Judgments [paper][code]
    Weiwen Xu, Deng Cai, Zhisong Zhang, Wai Lam, Shuming Shi
    ACL 2024 Findings

  • From Clozing to Comprehending: Retrofitting Pre-trained Masked Language Model to Pre-trained Machine Reader [paper][code]
    Weiwen Xu, Xin Li, Wenxuan Zhang, Meng Zhou, Wai Lam, Luo Si, Lidong Bing
    NeurIPS 2023

  • mPMR: A Multilingual Pre-trained Machine Reader at Scale [paper][code]
    Weiwen Xu, Xin Li, Wai Lam, Lidong Bing
    ACL 2023

  • PeerDA: Data Augmentation via Modeling Peer Relation for Span Identification Tasks [paper][code]
    Weiwen Xu, Xin Li, Yang Deng, Lidong Bing, Wai Lam
    ACL 2023

  • Nonfactoid question answering as query-focused summarization with graph-enhanced multihop inference [paper]
    Yang Deng, Wenxuan Zhang, Weiwen Xu, Ying Shen, Wai Lam.
    TNNLS 2023

  • A Unified Multi-task Learning Framework for Multi-goal Conversational Recommender Systems [arxiv]
    Yang Deng, Wenxuan Zhang, Weiwen Xu, Wenqiang Lei, Tat-Seng Chua, Wai Lam.
    TOIS 2023

  • ConReader: Exploring Implicit Relations in Contracts for Contract Clause Extraction [paper][code]
    Weiwen Xu, Yang Deng, Wenqiang Lei, Wenlong Zhao, Tat-Seng Chua, Wai Lam.
    EMNLP 2022

  • Exploiting reasoning chains for multi-hop science question answering [paper][code]
    Weiwen Xu, Yang Deng, Huihui Zhang, Deng Cai, Wai Lam.
    EMNLP 2021 Findings

  • Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering [paper][code]
    Weiwen Xu, Huihui Zhang, Deng Cai, Wai Lam.
    ACL 2021 Findings

  • Addressing the Vulnerability of NMT in Input Perturbations [paper]
    Weiwen Xu, Ai Ti Aw, Yang Ding, Kui Wu, Shafiq Joty.
    NAACL 2021 Industry Track

  • Revisit automatic error detection for wrong and missing translation–a supervised approach [paper]
    Wenqiang Lei, Weiwen Xu, Ai Ti Aw, Yuanxin Xiang, Tat-Seng Chua.
    EMNLP 2019

Professional Service

  • Conference Reviwer: EMNLP2023, ACL2023, SIGIR2023, IJCAI2023, ECIR2023, EMNLP2022, NAACL2022, ACL2021, EMNLP2021, NAACL2021,
  • Journal Reviewer: TACL, Knowledge-Based Systems, ACM Trans. on Web, Neurocomputing