I’m now a Ph.D. candidate in School of Intelligence Science and Technology at Peking University, working with Prof. Y. Zhang. I obtained my bachelor’s degree from the School of Computer Science and Engineering, UESTC in June 2021, under the supervision of Prof. K. Zheng. I’ve also spent time at Baidu, MSRA, Alibaba and Huawei.
My current research interests include Information Retrieval and Large Language Models. If you are also interested, please feel free to drop me an email.
🔥 News
- 2024.04: 🎉🎉 Nominated for the Academic Star Award!
- 2023.12: 🎉🎉 My paper entitled “Towards Verifiable Text Generation with Evolving Memory and Self-Reflection” is available on Arxiv!
- 2023.10: 🎉🎉 My paper entitled “LEAD: Liberal Feature-based Distillation for Dense Retrieval” was accepted by WSDM 2024!
- 2023.10: 🎉🎉 My paper entitled “Allies: Prompting Large Language Model with Beam Search” was accepted by EMNLP 2023!
- 2023.08: 🎉🎉 Awarded as Stars of Tomorrow during an internship at Microsoft!
📒 Preprint
![sym](../images/vtg.jpg)
Towards Verifiable Text Generation with Evolving Memory and Self-Reflection
Hao Sun, H. Cai, B. Wang, Y. Hou, X. Wei, S. Wang, Y. Zhang, D. Yin
Arxiv, 2024
Improving citation generation with a two-tier verifier and active retrieval mechanism.
![sym](../images/ricp.jpg)
Retrieved In-Context Principles from Previous Mistakes
Hao Sun, Y. Jiang, B. Wang, Y. Hou, Y. Zhang, P. Xie, F. Huang
Arxiv, 2024
Enabling LLMs to learn from mistakes by proving question-level and task-level principles.
![sym](../images/adaswitch.jpg)
Hao Sun, J. Wu, H. Cai, X. Wei, Y. Feng, B. Wang, S. Wang, Y. Zhang, D. Yin
Arxiv, 2024
Enabling adaptive switching between local agent and cloud agent through collaborative learning.
![sym](../images/simcns.jpg)
SimCNS: Simple Curriculum Negative Sampling for Multi-Source Dense Retrieval
Hao Sun, X. Liu, Y. Gong, A. Dong, G. Shi, Y. Zhang, L. Yang, N. Duan
Arxiv, 2024
Select the most important negative samples for multi-source dense retrieval
📝 Publications
![sym](../images/LEAD.jpg)
LEAD: Liberal Feature-based Distillation for Dense Retrieval
Hao Sun, X. Liu, Y. Gong, A. Dong, J. Lu, Y. Zhang, L. Yang, R. Majumder, N. Duan
The ACM International Conference on Web Search and Data Mining (WSDM), 2024, Oral
Distill the intermediate features from teacher to student without the constraints on model architecture or tokenizers.
![sym](../images/allies.jpg)
Allies: Prompting Large Language Model with Beam Search
Hao Sun, X. Liu, Y. Gong, Y. Zhang, N. Duan
The Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023, Findings
Improving the knowledge scope and robustness of LLMs with Beam Search.
![sym](../images/hsge.jpg)
History Semantic Graph Enhanced Conversational KBQA with Temporal Information Modeling
Hao Sun, Y.g Li, L. Deng, B. Li, B. Hui, B. Li, Y. Lan, Y. Zhang, Y. Li
The Annual Meeting of the Association for Computational Linguistics (ACL), 2023
Modeling history conversation information with History Semantic Graph.
![sym](../images/conlearn.jpg)
Hao Sun, Y. Li, Y. Zhang
The SIAM International Conference on Data Mining (SDM), 2022
Capturing complex transition patterns between concepts through Graph Neural Network.
![sym](../images/periodicmove.jpg)
PeriodicMove: Shift-aware Human Mobility Recovery with Graph Neural Network
Hao Sun, C. Y.g, L. Deng, F. Zhou, F. Huang, K. Zheng
The ACM International Conference on Information and Knowledge Management (CIKM), 2021
Capturing multi-level periodicity and shifting periodicity of human mobility using attention mechanism.
![sym](../images/pdkr.jpg)
Personalized Dynamic Knowledge-Aware Recommendation with Hybrid Explanations
Hao Sun, Z. Wu, Y. Cui, L. Deng, Y. Zhao, K. Zheng
The International Conference on Database Systems for Advanced Applications (DASFAA), 2021
Providing personalized and hybrid explanations for the recommendations.
![sym](../images/s2tul.jpg)
S2TUL: A Semi-Supervised Framework for Trajectory-User Linking
L. Deng, Hao Sun, Y. Zhao, S. Liu, K. Zheng
The ACM International Conference on Web Search and Data Mining (WSDM), 2023
Capture fine-grained intra-trajectory information by passing the trajectories into the sequential neural networks.
![sym](../images/nci.jpg)
A Neural Corpus Indexer for Document Retrieval
Y. Wang, Y. Hou, H. Wang, Z. Miao, S. Wu, Hao Sun, Q. Chen, Y. Xia, C. Chi, G. Zhao, Z. Liu, X. Xie, H. Allen Sun, W. Deng, Q. Zhang, M. Yang
The Annual Conference on Neural Information Processing Systems (NeurIPS), 2022
Propose an end-to-end differentiable document retrieval model that can significantly outperform both inverted index and dense retrieval solutions.
![sym](../images/CL-TSim.jpg)
Efficient Trajectory Similarity Computation with Contrastive Learning
L. Deng, Y. Zhao, Z. Fu, Hao Sun, S. Liu, K. Zheng
The ACM International Conference on Information and Knowledge Management (CIKM), 2022
Employ a contrastive learning mechanism to learn the representations of trajectories, which are then used to calculate the dissimilarity between them.
![sym](../images/3SGNN.jpg)
Efficient and Effective Similar Subtrajectory Search: A Spatial-aware Comprehension Approach
L. Deng, Hao Sun, R. Sun, Y. Zhao, H. Su
The ACM Transactions on Intelligent Systems and Technology (TIST), 2022
Propose a Similar Subtrajectory Search with a Graph Neural Networks framework.
![sym](../images/trill.jpg)
Fusing Local and Global Mobility Patterns for Trajectory Recovery
L. Deng, Y. Zhao, Hao Sun, C. Yang, J. Xie, K. Zheng
The ACM International Conference on Information and Knowledge Management (CIKM), 2022
Propose a neural attention model based on graph convolutional networks to enhance the accuracy of trajectory recovery.
![sym](../images/DisAug.jpg)
Boosting Disfluency Detection with Large Language Model as Disfluency Generator
Z. Cheng, J. Guo, Hao Sun, Y. Zhang
The IEEE International Conference on Multimedia & Expo (ICME), 2024
Propose a framework that addresses data sparsity issues by generating disfluent data using LLM as augmentation data.
![sym](../images/skr.jpg)
Sequential-Knowledge-Aware Next POI Recommendation: A Meta-Learning Approach
Y. Cui, Hao Sun, Y. Zhao, H. Yin, K. Zheng
The ACM Transactions on Information Systems (TOIS), 2021
Utilize sequential, spatiotemporal, and social knowledge to recommend the next POI for a location-based social network user.
🎖 Honors and Awards
- 2024.06 First Prize of Challenge Cup Competition, Peking University.
- 2024.03 Academic Star Nomination.
- 2023.09 Merit Student of Peking University.
- 2023.09 Schlumberger Scholarship.
- 2023.08 Stars of Tomorrow Award at Microsoft, Microsoft.
- 2023.06 First Prize of Challenge Cup Competition, Peking University.
- 2022.12 Outstanding Paper Award, NeurIPS 2022.
- 2021.06 Outstanding Graduation Thesis for Undergraduates, UESTC.
- 2021.06 Outstanding Graduate, UESTC.
- 2019.12 National Scholarship.
- 2018.09 National Scholarship.
📖 Educations
- 2021.09 - Present, Ph.D. Candidate, Peking University.
- 2017.09 - 2021.06, Undergraduate, University of Electronic Science And Technology of China.
📚 Academic Services
- Program Committee / Reviewer: ACL 2022-23, EMNLP 2022-23, WWW 2023, IJCAI 2023
- Secondary Reviewer: AAAI 2022, CIKM 2021-22, ICDM 2021-23, COLING 2022-23, DASFAA 2022-23
👩🏻🏫 Teaching
- Teaching Assistant, Computer Networks and Web Technologies, Peking University, Fall 2023
💻 Internships
- Baidu Research, focusing on large language models.
- Microsoft Research Asia (MSRA), focusing on dense retrieval.
- DAMO Academy, focusing on multi-turn conversation.
- HUAWEI Research, focusing on spatial-temporal data analysis.