Tianqing Fang
I got my Ph.D. degree from HKUST in the summer of 2024, supervised by Prof. Yangqiu Song. Previously, I was a visiting Ph.D. student at EPFL, working with Prof. Antoine Bosselut, a visiting research scholar at University of Southern California, working with Prof. Muhao Chen. I received my B.E. degree from Zhejiang University in 2019, supervised by Prof. Yang Yang. Here is my Curriculum Vitae (April 2024).
Research Interest
Current Topic:
- VLM/LLM-based Agent.
- Self-improvement and evolvement of Agent.
Topic in Ph.D.:
- Knowledge Acquisition: Commonsense knowledge acquisition at scale using information extraction (ASER) and knowledge base population (DISCOS, CKBP, PseudoReasoner); Conceptualization knowledge acquisition (AbstractATOMIC, CAT).
- Reasoning with knowledge for (Large) Language Models: Integration of (abstract) commonsense knowledge to language models (CAR); Complex reasoning over knowledge graphs (COM2); Knowledge constrained decoding for LLMs (KCTS); Knowledge conflicts detection and mitigation (CDA); Dialogue system with knowledge.
- Machine Learning for NLP: Data denoising (ODDA), training dynamics (QAD), …
News
- 8/2024: Successfully defended my Ph.D.!
- 5/2024: 3 papers accepted to ACL main conference!
- 5/2024: Our original paper of conceptualization is finally accepted by Artifitial Intelligence journal after two years (many of the follow-up works are already accepted by conferences though). Big shout out to Mutian, who has put tremendous efforts into this amazing work.
- 4/2024: Invited to serve as Senior Area Chair of ACL ARR in April 2024!
- 3/2024: 2 papers accepted to Findings of NAACL 2024!
- 2/2024: Invited to serve as Area Chair of ACL 2024.
- 1/2024: 3 papers accepted to EACL 2024 and 1 paper accepted to ICLR 2024!
- 1/2024: Invited to serve as PC for NAACL 2024 and IJCAI 2024.
- 10/2023: Invited to serve as the PC for COLING-LREC 2024, and the reviewer for EACL 2023 (ARR).
- 10/2023: 5 papers accepted to EMNLP. Topics includes zero-shot commonsense QA (2 findings), knowledge-constrained decoding (main), a benchmark for analogy reasoning (main), a benchmark for academic writing formalization (main).
Publication
Preprint
Kaiqiao Han*, Tianqing Fang *, Zhaowei Wang, Yangqiu Song, Mark Steedman.
Concept-Reversed Winograd Schema Challenge: Evaluating and Improving Robust Reasoning in Large Language Models via Abstraction
[paper]Zhaowei Wang, Hongming Zhang, Tianqing Fang, Ye Tian, Yue Yang, Kaixin Ma, Xiaoman Pan, Yangqiu Song, Dong Yu.
DivScene: Benchmarking LVLMs for Object Navigation with Diverse Scenes and Objects
[paper] [code]Mengzhao Jia, Wenhao Yu, Kaixin Ma, Tianqing Fang, Zhihan Zhang, Siru Ouyang, Hongming Zhang, Meng Jiang, Dong Yu.
LEOPARD: A Vision Language Model For Text-Rich Multi-Image Tasks
[paper] [code]Hongliang He, Wenlin Yao, Kaixin Ma, Wenhao Yu, Hongming Zhang, Tianqing Fang, Zhenzhong Lan and Dong Yu
OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization
[paper] [code]
Journal
2024
- Mutian He, Tianqing Fang, Weiqi Wang, and Yangqiu Song.
Acquiring and Modelling Abstract Commonsense Knowledge via Conceptualization,
Artificial Intelligence, 2024. [paper] [code]
2022
- Hongming Zhang*, Xin Liu*, Haojie Pan*, Haowen Ke, Jiefu Ou, Tianqing Fang, and Yangqiu Song.
ASER: Towards Large-scale Commonsense Knowledge Acquisition via Higher-order Selectional Preference over Eventualities.
Artificial Intelligence, 2022. [paper] [arxiv] [code] [homepage]
Conference
2024
Tianqing Fang, Zeming Chen, Yangqiu Song, Antoine Bosselut.
Complex Reasoning over Logical Queries on Commonsense Knowledge Graphs
ACL 2024. [paper][code]Weiqi Wang, Tianqing Fang, Chunyang Li, Haochen Shi, Wenxuan Ding, Baixuan Xu, Zhaowei Wang, Jiaxin Bai, Xin Liu, Jiayang Cheng, Chunkit Chan, Yangqiu Song.
CANDLE: Iterative Conceptualization and Instantiation Distillation from Large Language Models for Commonsense Reasoning., 2024
ACL 2024. [paper] [code&data]Zhaowei Wang, Wei Fan, Qing Zong, Hongming Zhang, Sehyun Choi, Tianqing Fang, Xin Liu, Yangqiu Song, Ginny Y. Wong, Simon See.
AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation Tuning with Plausibility Estimation
ACL 2024. [paper] [code&data]Tianqing Fang, Zhaowei Wang, Wenxuan Zhou, Hongming Zhang, Yangqiu Song, Muhao Chen.
Getting Sick After Seeing a Doctor? Diagnosing and Mitigating Knowledge Conflicts in Event Temporal Reasoning,
Findings of NAACL 2024 [paper]Zhaowei Wang, Haochen Shi, Weiqi Wang, Tianqing Fang, Hongming Zhang, Sehyun Choi, Xin Liu, Yangqiu Song
AbsPyramid: Benchmarking the Abstraction Ability of Language Models with a Unified Entailment Graph
Findings of NAACL 2024 [paper]Tianqing Fang, Wenxuan Zhou, Fangyu Liu, Hongming Zhang, Yangqiu Song, and Muhao Chen.
On-the-fly Denoising for Data Augmentation in Natural Language Understanding,
Findings of EACL 2024 [paper]Chunkit Chan, Jiayang Cheng, Weiqi Wang, Yuxin Jiang, Tianqing Fang, Xin Liu, Yangqiu Song.
ChatGPT Evaluation on Sentence Level Relations: A Focus on Temporal, Causal, and Discourse Relations,
Findings of EACL 2024 [paper]Quyet V. Do, Tianqing Fang, Shizhe Diao, Zhaowei Wang, Yangqiu Song.
ConstraintChecker: A Plugin for Large Language Models to Reason on Commonsense Knowledge Bases
EACL 2024 [paper]Xiongye Xiao, Gengshuo Liu, Gaurav Gupta, Defu Cao, Shixuan Li, Yaxing Li, Tianqing Fang, Mingxi Cheng, Paul Bogdan.
Neuro-Inspired Hierarchical Multimodal Learning,
ICLR 2024 [paper]Baixuan Xu*, Weiqi Wang*, Haochen Shi, Wenxuan Ding, Huihao Jing, Tianqing Fang, Jiaxin Bai, Xin Liu, Changlong Yu, Zheng Li, Chen Luo, Qingyu Yin, Bing Yin, Long Chen, Yangqiu Song.
MIND: Multimodal Shopping Intention Distillation from Large Vision-language Models for E-commerce Purchase Understanding.
EMNLP 2024 [paper] [code]Wenxuan Ding*, Weiqi Wang*, Sze Heng Douglas Kwok, Minghao Liu, Tianqing Fang, Jiaxin Bai, Xin Liu, Changlong Yu, Zheng Li, Chen Luo, Qingyu Yin, Bing Yin, Junxian He, Yangqiu Song.
IntentionQA: A Benchmark for Evaluating Purchase Intention Comprehension Abilities of Language Models in E-commerce.
Findings of EMNLP 2024 [paper] [code]
2023
Sehyun Choi, Tianqing Fang, Zhaowei Wang, Yangqiu Song
KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023 (Main Conference), [paper] [code]Jiayang Cheng, Lin Qiu, Tsz Ho CHAN, Tianqing Fang, Weiqi Wang, Chunkit Chan, Qipeng Guo, Hongming Zhang, Yangqiu Song, Yue Zhang, Zheng Zhang
STORYANALOGY: Deriving Story-level Analogies from Large Language Models to Unlock Analogical Understanding
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023 (Main Conference), [paper] [code&data]Shizhe Diao, Yongyu Lei, Liangming Pan, Tianqing Fang, Wangchunshu Zhou, Sedrick Scott Keh, Min-Yen Kan, Tong Zhang
Doolittle: Benchmarks and Corpora for Academic Writing Formalization
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023 (Main Conference), [paper] [code&data]Weiqi Wang*, Tianqing Fang*, Wenxuan Ding, Baixuan Xu, Xin Liu, Yangqiu Song, Antoine Bosselut.
CAR: Conceptualization-Augmented Reasoner for Zero-Shot Commonsense Question Answering, 2023
Findings of Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP), 2023. [paper] [code]Haochen SHI, Weiqi Wang, Tianqing Fang, Baixuan Xu, Wenxuan Ding, Xin Liu, Yangqiu Song
QADYNAMICS: Training Dynamics-Driven Synthetic QA Diagnostic for Zero-Shot Commonsense Question Answering
Findings of Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP), 2023. [paper] [code]Weiqi Wang*, Tianqing Fang*, Baixuan Xu, Chun Yi Louis Bo, Yangqiu Song, Lei Chen.
🐈CAT: A Contextualized Conceptualization and Instantiation Framework for Commonsense Reasoning
Annual Meeting of the Association for Computational Linguistics (ACL), 2023. [pdf] [code].Zhaowei Wang, Quyet V. Do, Hongming Zhang, Jiayao Zhang, Weiqi Wang, Tianqing Fang, Yangqiu Song, Ginny Y. Wong, Simon See
COLA: Contextualized Commonsense Causality Reasoning from the Causal Inference Perspective
Annual Meeting of the Association for Computational Linguistics (ACL), 2023. [pdf] [code].
2022
Tianqing Fang, Quyet V. Do, Hongming Zhang, Yangqiu Song, Ginny Y. Wong and Simon See.
PseudoReasoner: Leveraging Pseudo Labels for Commonsense Knowledge Base Population.
Findings of Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP), 2022. [pdf] [code].
Internship work at NVIDIAYing Su, Zihao Wang, Tianqing Fang, Hongming Zhang, Yangqiu Song and Tong Zhang.
MICO: A Multi-alternative Contrastive Learning Framework for Commonsense Knowledge Representation.
Findings of Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP), 2022. [pdf] [code].Zhaowei Wang, Hongming Zhang, Tianqing Fang, Yangqiu Song, Ginny Y. Wong and Simon See.
SubeventWriter: Iterative Sub-event Sequence Generation with Coherence Controller.
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2022. [pdf] [code].Ziqian Zeng, Weimin Ni, Tianqing Fang, Xiang Li, Xinran Zhao, and Yangqiu Song.
Weakly Supervised Text Classification using Supervision Signals from a Language Model.
Findings of Annual Conference of the North American Chapter of the Association for Computational Linguistics (Findings of NAACL), 2022. [pdf] [code].
2021
Tianqing Fang*, Weiqi Wang*, Sehyun Choi, Shibo Hao, Hongming Zhang, Yangqiu Song, Bin He.
Benchmarking Commonsense Knowledge Base Population with an Effective Evaluation Dataset.
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021 (Main Conference), [pdf] [v2] [code] [video]- Tianqing Fang, Haojie Pan, Hongming Zhang, Yangqiu Song, Kun Xu, Dong Yu.
Do Boat and Ocean Suggest Beach? Dialogue Summarization with External Knowledge.
Conference on Automated Knowledge Base Construction (AKBC), 2021. [pdf] [code] - Nedjma Ousidhoum, Xinran Zhao, Tianqing Fang, Yangqiu Song, and Dit-Yan Yeung.
Probing Toxic Content in Large Pre-Trained Language Models.
Annual Meeting of the Association for Computational Linguistics (ACL), 2021. [pdf] [code] - Tianqing Fang, Hongming Zhang, Weiqi Wang, Yangqiu Song, and Bin He.
DISCOS: Bridging the Gap between Discourse Knowledge and Commonsense Knowledge.
The Web Conference (WWW), 2021. [pdf] [code] [video]
*: Equal Contribution
Ph.D. thesis:
Commonsense Knowledge Base Population and Reasoning for Inferential Knowledge. [pdf]
Awards
- HKUST Overseas Research Award (2023)
- HKUST RedBird Academic Excellence Award for Continuing PhD Students in 2022/23 (2023)
- HKUST RedBird Academic Excellence Award for Continuing PhD Students in 2021/22 (2022)
- Hong Kong Ph.D. Fellowship (2019-2023)
- Special Scholarship for Undergraduate Students in Zhejiang University (one of the top honor in ZJU) (2018)
- Provincial Scholarship (top 5%, ZJU, 2018)
- 1st Place and MATLAB Innovation Award (1st/36K+) in Contemporary Undergraduate Mathematical Contest in Modeling (2017)
- Provincial Scholarship (top 5%, ZJU, 2017)
- National Scholarship (top 3%, ZJU, 2016)
Teaching
- MSBD 5018: Natural Language Processing (Spring 2022)
- COMP5222/MATH5471: Statistical Learning Models for Text and Graph Data. (Fall 2021)
- MSBD6000H: Natural Language Processing. (Spring 2021)
- COMP4901K/MATH4824B: Machine Learning for Natural Language Processing. (Fall 2020)
- COMP4332/RMBI4310: Big Data Mining. (Spring 2020)
Academic Service
- Conference Area Chair: ARR (Feb/April, 24) -> ACL 2024, EMNLP 2024
- Conference Reviewer: ACL Rolling Review, AAAI’23-24, ACL’23, COLING’22-24, EMNLP’22-23, IJCAI’23-24, KDD’23-24
- Conference External Reviewer: KDD’20, 21, ACL’21, EMNLP’21
Miscs:
Check out some of my photography works on unsplash.