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 KongSep. 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 FindingsFrom 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 2023mPMR: A Multilingual Pre-trained Machine Reader at Scale [paper][code]
Weiwen Xu, Xin Li, Wai Lam, Lidong Bing
ACL 2023PeerDA: Data Augmentation via Modeling Peer Relation for Span Identification Tasks [paper][code]
Weiwen Xu, Xin Li, Yang Deng, Lidong Bing, Wai Lam
ACL 2023Nonfactoid question answering as query-focused summarization with graph-enhanced multihop inference [paper]
Yang Deng, Wenxuan Zhang, Weiwen Xu, Ying Shen, Wai Lam.
TNNLS 2023A 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 2023ConReader: 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 2022Exploiting reasoning chains for multi-hop science question answering [paper][code]
Weiwen Xu, Yang Deng, Huihui Zhang, Deng Cai, Wai Lam.
EMNLP 2021 FindingsDynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering [paper][code]
Weiwen Xu, Huihui Zhang, Deng Cai, Wai Lam.
ACL 2021 FindingsAddressing the Vulnerability of NMT in Input Perturbations [paper]
Weiwen Xu, Ai Ti Aw, Yang Ding, Kui Wu, Shafiq Joty.
NAACL 2021 Industry TrackRevisit 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