Selected Papers
Can Pre-training Indicators Reliably Predict Fine-tuning Outcomes of LLMs?
Hansi Zeng, Hui, Kai, Honglei Zhuang, Zhen Qin, Zhenrui Yue, Hamed Zamani, Dana Alon arXiv preprint
[PDF]
Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting
Zhen Qin, Rolf Jagerman, Hui, Kai, Honglei Zhuang, Junru Wu, Le Yan, Jiaming Shen, Tianqi Liu, Jialu Liu, Donald Metzler, Xuanhui Wang, Michael Bendersky in NAACL: Findings 2024
[PDF]
GECKO: Versatile Text Embeddings Distilled from Large Language Models
Jinhyuk Lee, Zhuyun Dai, Xiaoqi Ren, Blair Chen, Daniel Cer, Jeremy R Cole, Hui, Kai, Michael Boratko, Rajvi Kapadia, Wen Ding, Yi Luan, Sai Meher Karthik Duddu, Gustavo Hernandez Abrego, Weiqiang Shi, Nithi Gupta, Aditya Kusupati, Prateek Jain, Siddhartha Reddy Jonnalagadda, Ming-Wei Chang, Iftekhar Naim arXiv preprint
[PDF]
How Does Generative Retrieval Scale to Millions of Passages?
Ronak Pradeep, Hui, Kai, Jai Gupta, Ádám Dániel Lelkes, Honglei Zhuang, Jimmy Lin, Donald Metzler, Vinh Q. Tran in EMNLP: 2023
[PDF]
Transformer Memory as a Differentiable Search Index
Yi Tay, Vinh Q Tran, Mostafa Dehghani, Jianmo Ni, Dara Bahri, Harsh Mehta, Zhen Qin, Hui, Kai, Zhe Zhao, Jai Gupta, Tal Schuster, William W Cohen, Donald Metzler
in NeurIPS: 2022
[PDF]
ED2LM: Encoder-Decoder to Language Model for Faster Document Re-ranking Inference
Hui, Kai, Honglei Zhuang, Tao Chen, Zhen Qin, Jing Lu, Dara Bahri, Ji Ma, Jai Gupta, Cicero Nogueira dos Santos, Yi Tay, Donald Metzler
in ACL: Findings 2022
[PDF]
Incorporating Ranking Context for End-to-End BERT Re-ranking
Xiaoyang Chen, Hui, Kai, Ben He, Xianpei Han, Le Sun, Zheng Ye
in ECIR: 2022
[PDF]
Ext5: Towards extreme multi-task scaling for transfer learning
Vamsi Aribandi, Yi Tay, Tal Schuster, Jinfeng Rao, Huaixiu Steven Zheng, Sanket Vaibhav Mehta, Honglei Zhuang, Vinh Q. Tran, Dara Bahri, Jianmo Ni, Jai Gupta, Hui, Kai, Sebastian Ruder, Donald Metzler
in ICLR 2022
[PDF]
Question Answering using Web Lists
A. R. Katti, Hui, Kai, A. de Gispert, and H. Fuerstenau
in CIKM 2021 (Short paper)
[PDF]
Contextualized Offline Relevance Weighting for Efficient and Effective Neural Retrieval
X. Chen, B. He, Hui, Kai, Y. Wang, L. Sun, and Y. Sun
in SIGIR 2021 (Best short paper award)
[PDF]
Simplified TinyBERT: Knowledge Distillation for Document Retrieval
X. Chen, B. He, Hui, Kai, L. Sun, and Y. Sun
in ECIR 2021 (Short paper)
[PDF]
BERT-QE: Contextualized Query Expansion for Document Re-ranking
Z. Zheng, Hui, Kai, B. He, X. Han, L. Sun, and A. Yates
in EMNLP 2020: Findings
[PDF] [Code]
Content-Based Weak Supervision for Ad-Hoc Re-Ranking
S. MacAvaney, A. Yates, Hui, Kai, and O. Frieder
in SIGIR 19 (Short paper)
[PDF]
Co-PACRR: A Context-Aware Neural IR Model for Ad-hoc Retrieval
Hui, Kai, A. Yates, K. Berberich, and G. de Melo
in WSDM 18
[PDF] [Poster] [Code]
NPRF: A Neural Pseudo Relevance Feedback Framework for Ad-hoc Information Retrieval
C. Li, Y. Sun, B. He, L. Wang, Hui, Kai, A. Yates, L. Sun, and J. Xu
in EMNLP 2018
[PDF]
TDNN: A Two-stage Deep Neural Network for Prompt-independent Automated Essay Scoring
C. Jin, B. He, Hui, Kai, and L. Sun
in ACL 2018
[PDF]
Characterizing Question Facets for Complex Answer Retrieval
S. MacAvaney, A. Yates, A. Cohan, L. Soldaini, Hui, Kai, N. Goharian, and O. Frieder
in SIGIR 2018 (Short paper)
[PDF]
PACRR: A Position-Aware Neural IR Model for Relevance Matching
Hui, Kai, A. Yates, K. Berberich, and G. de Melo
in EMNLP 17
[PDF] [Slide] [Code]
Position-Aware Representations for Relevance Matching in Neural Information Retrieval
Hui, Kai, A. Yates, K. Berberich, and G. de Melo
in WWW 17 (Poster)
[PDF]
Transitivity, Time Consumption, and Quality of Preference Judgments in Crowdsourcing
Hui, Kai and K. Berberich
in ECIR 2017
[PDF] [Slide] [Poster] [Data]
Contextualized PACRR for Complex Answer Retrieval
S. MacAvaney, A. Yates, Hui, Kai
in TREC 2017
[PDF]
Dealing with Incomplete Judgments in Cascade Measures
Hui, Kai, K. Berberich, and I. Mele
in ICTIR 2017
[PDF] [Slide]
A document-based neural relevance model for effective clinical decision support
Y. Ran, B. He, Hui, Kai, J. Xu, and L. Sun
in BIBM 2017
[PDF]
Low-Cost Preference Judgment via Ties
Hui, Kai and K. Berberich
in ECIR 17 (Short Paper)
[PDF] [Poster]
Merge-Tie-Judge: Low-Cost Preference Judgments with Ties
Hui, Kai and K. Berberich
in ICTIR 2017 (Short paper)
[PDF] [Poster]
Cluster Hypothesis in Low-Cost IR Evaluation with Different Document Representations
Hui, Kai and K. Berberich
in WWW 16 (Poster)
[PDF] [Poster]
Selective Labeling and Incomplete Label Mitigation for Low-Cost Evaluation
Hui, Kai and K. Berberich
in SPIRE 15
[PDF] [Slide]
Sponsored Search Ad Selection by Keyword Structure Analysis
Hui, Kai, B. Gao, B. He, and T. Luo
in ECIR 2013
[PDF] [Slide]
Relevance weighting using within-document term statistics
Hui, Kai, B. He, T. Luo, and B. Wang
in CIKM 2011 (Short paper)
[PDF] [Slide]
A Comparative Study of Pseudo Relevance Feedback for Ad-hoc Retrieval
Hui, Kai, B. He, T. Luo, and B. Wang
in ICTIR 2011 (Poster)
[PDF]
GUCAS at TREC 2011 Microblog Track
X. Zhang, Hui, Kai, B. He, T. Luo
in TREC 2011
Contextualized query expansion via unsupervised chunk selection for text retrieval
Z. Zheng, Hui, Kai, B. He, X. Han, L. Sun, and A. Yates
Information Processing & Management, 2021
[PDF]
Overcoming Low-Utility Facets for Complex Answer Retrieval
S. MacAvaney, A. Yates, A. Cohan, L. Soldaini, Hui, Kai, N. Goharian, and O. Frieder
Information Retrieval Journal, 2019
[PDF]
Neural relevance model using similarities with elite documents for effective clinical decision support
Y. Ran, B. He, Hui, Kai, J. Xu, and L. Sun
International Journal of Data Mining and Bioinformatics, 2018
Dissertation
Automatic methods for low-cost evaluation and position-aware models for neural information retrieval
Kai Hui
PhD Thesis, Saarbrücken, Germany, 2017
[PDF] [Slide]