Zhengbao Jiang (江政宝)
I am a PhD student at Language Technologies Institute of Carnegie Mellon University. I am fortunate to be advised by Graham Neubig, working on Natural Language Processing, Information Retrieval, and Machine Learning. I focus on addressing knowledge-intensive tasks such as QA and reasoning through either nonparametric methods (i.e., retrieval-augmented generation) or parametric methods (i.e., knowledge updates on LLMs followed by close-book prompting).
I received my Bachelor’s and Master’s degree in Computer Science from Renmin University of China in 2015 and 2018, where I worked with Zhicheng Dou, Wayne Xin Zhao, Jian-Yun Nie, and Ji-Rong Wen on IR and NLP.
I’m on the industry job market (2024)! Please feel free to reach out!
Google Scholar | Semantic Scholar | Github | CV
Research Interests
- RAG: nonparametric LLMs through retrieval-augmented generation. [FLARE] [ReAtt]
- Alignment: Alignment/Calibration for factuality and truthfulness. [pre-instruction-tuning] [QA calibration]
- Prompting: Eliciting factual knowledge from LMs through prompt learning/engineering. [LPAQA] [X-FACTR]
- Reasoning: Improving reasoning capacity through synthetic pre-training. [OmniTab] [multihop QA]
Experience
- 2023.6 - 2023.12, Research Intern, FAIR at Meta
Mentor: Srini Iyer, Scott Wen-tau Yih, Xi Victoria Lin, Pedro Rodriguez - 2022.6 - 2022.12, Research Intern, FAIR at Meta
Mentor: Fabio Petroni, Jane Yu, Timo Schick, Patrick Lewis - 2021.6 - 2021.12, Research Intern, Microsoft
Mentor: Yi Mao, Pengcheng He, Weizhu Chen - 2020.6 - 2020.9, Research Intern, Amazon
Mentor: Jialong Han, Xin Luna Dong - 2017.10 - 2018.3, Research Intern, Alibaba, AI labs
Mentor: Zaiqing Nie - 2017.7 - 2017.10, Research Intern, Microsoft Research Asia
Mentor: Zaiqing Nie - 2014.2 - 2014.12, Software Engineer, OfferCalendar (startup)
Publications (* indicates equal contribution)
- Instruction-tuned Language Models are Better Knowledge Learners [PDF][Code]
Zhengbao Jiang, Zhiqing Sun, Weijia Shi, Pedro Rodriguez, Chunting Zhou, Graham Neubig, Xi Victoria Lin, Wen-tau Yih, Srinivasan Iyer
arXiv - Active Retrieval Augmented Generation [PDF][Code]
Zhengbao Jiang*, Frank F. Xu*, Luyu Gao*, Zhiqing Sun*, Qian Liu, Jane Dwivedi-Yu, Yiming Yang, Jamie Callan, Graham Neubig
EMNLP’23 - From Zero to Hero: Examining the Power of Symbolic Tasks in Instruction Tuning [PDF][Code]
Qian Liu*, Fan Zhou*, Zhengbao Jiang, Longxu Dou, Min Lin
arXiv - GPTScore: Evaluate as You Desire [PDF][Code]
Jinlan Fu, See-Kiong Ng, Zhengbao Jiang, Pengfei Liu
arXiv - Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformer [PDF][Code]
Zhengbao Jiang*, Luyu Gao*, Jun Araki, Haibo Ding, Zhiruo Wang, Jamie Callan, Graham Neubig
EMNLP’22 (oral) - PEER: A Collaborative Language Model [PDF]
Timo Schick, Jane Dwivedi-Yu, Zhengbao Jiang, Fabio Petroni, Patrick Lewis, Gautier Izacard, Qingfei You, Christoforos Nalmpantis, Edouard Grave, Sebastian Riedel
ICLR’23 - EditEval: An Instruction-Based Benchmark for Text Improvements [PDF]
Jane Dwivedi-Yu, Timo Schick, Zhengbao Jiang, Maria Lomeli, Patrick Lewis, Gautier Izacard, Edouard Grave, Sebastian Riedel, Fabio Petroni
arXiv - DocPrompting: Generating Code by Retrieving the Docs [PDF]
Shuyan Zhou, Uri Alon, Frank F. Xu, Zhiruo Wang, Zhengbao Jiang, Graham Neubig
ICLR’23 - OmniTab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question Answering [PDF][Code]
Zhengbao Jiang, Yi Mao, Pengcheng He, Graham Neubig, Weizhu Chen
NAACL’22 (oral) - Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing [PDF][Website]
Pengfei Liu, Weizhe Yuan, Jinlan Fu, Zhengbao Jiang, Hiroaki Hayashi, Graham Neubig
ACM CSUR’22 - Understanding and Improving Zero-shot Multi-hop Reasoning in Generative Question Answering [PDF][Code]
Zhengbao Jiang, Jun Araki, Haibo Ding, Graham Neubig
COLING’22 (oral) - Table Retrieval May Not Necessitate Table-specific Model Design [PDF][Code]
Zhiruo Wang, Zhengbao Jiang, Eric Nyberg, Graham Neubig
NAACL’22 (SUKI workshop) - How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering [PDF]
Zhengbao Jiang, Jun Araki, Haibo Ding, Graham Neubig
TACL’21 - CoRI: Collective Relation Integration with Data Augmentation for Open Information Extraction [PDF]
Zhengbao Jiang, Jialong Han, Bunyamin Sisman, Xin Luna Dong
ACL’21 - GSum: A General Framework for Guided Neural Abstractive Summarization [PDF]
Zi-Yi Dou, Pengfei Liu, Hiroaki Hayashi, Zhengbao Jiang, Graham Neubig
NAACL’21 - X-FACTR: Multilingual Factual Knowledge Retrieval from Pretrained Language Models [PDF][Code]
Zhengbao Jiang*, Antonios Anastasopoulos*, Jun Araki, Haibo Ding, Graham Neubig
EMNLP’20 - How Can We Know What Language Models Know? [PDF][Code]
Zhengbao Jiang*, Frank F. Xu*, Jun Araki, Graham Neubig
TACL’20 (oral) - Generalizing Natural Language Analysis through Span-relation Representations [PDF][Code]
Zhengbao Jiang, Wei Xu, Jun Araki, Graham Neubig
ACL’20 - Incorporating External Knowledge through Pre-training for Natural Language to Code Generation [PDF][Code]
Frank F. Xu*, Zhengbao Jiang*, Pengcheng Yin, Bogdan Vasilescu, Graham Neubig
ACL’20 (short) - Graph-Revised Convolutional Network [PDF][Code]
ECML’20
Donghan Yu, Ruohong Zhang, Zhengbao Jiang, Yuexin Wu, Yiming Yang - Learning Relation Entailment with Structured and Textual Information [PDF][Code]
Zhengbao Jiang, Jun Araki, Donghan Yu, Ruohong Zhang, Wei Xu, Yiming Yang, Graham Neubig
AKBC’20 - Improving Open Information Extraction via Iterative Rank-Aware Learning [PDF][Code]
Zhengbao Jiang, Pengcheng Yin, Graham Neubig
ACL’19 (short) - Personalizing Search Results Using Hierarchical RNN with Query-aware Attention [PDF]
Songwei Ge, Zhicheng Dou, Zhengbao Jiang, Jian-Yun Nie, Ji-Rong Wen
CIKM’18 - Supervised Search Result Diversification via Subtopic Attention [PDF]
Zhengbao Jiang, Zhicheng Dou, Wayne Xin Zhao, Jian-Yun Nie, Ming Yue, Ji-Rong Wen
TKDE’18 - Learning to Diversify Search Results via Subtopic Attention [PDF][Slide][Code]
Zhengbao Jiang, Ji-Rong Wen, Zhicheng Dou, Wayne Xin Zhao, Jian-Yun Nie, Ming Yue
SIGIR’17 - Generating Query Facets Using Knowledge Bases [PDF]
Zhengbao Jiang, Zhicheng Dou, Ji-Rong Wen
TKDE’17 - Automatically Mining Facets for Queries from Their Search Results [PDF]
Zhicheng Dou, Zhengbao Jiang, Sha Hu, Ji-Rong Wen, Ruihua Song
TKDE’16