Publications

* means corresponding author, + indicates that author names or major contributors are listed in alphabetical order. You can also find my articles on my Google Scholar profile.

2026

• Mengyi Yan, Yaoshu Wang, Guangyi Zhang, Kehan Pang, Haoyi Zhou*,
  Accelerating Influence Function Estimation for Large Language Models: A Practical Design,
  The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2026, CCF-A)

• Yang Liu, Mengyi Yan*, Jiao Xue, Weilong Ren, Yutong Ye, Haoyi Zhou, Jianxin Li*, Zhumin Chen,
  SPARQ: A Cost-Efficient Framework for Offline Table Question Answering via Adaptive Routing,
  The 42nd IEEE International Conference on Data Engineering (ICDE 2026, CCF-A) [Paper] [Code]

2025

• Mengyi Yan, Yaoshu Wang*, Yue Wang, Xiaoye Miao, Jianxin Li,
  GIDCL: A Graph-Enhanced Interpretable Data Cleaning Framework with Large Language Models,
  The 2025 ACM Conference on Management of Data (SIGMOD 2025, CCF-A) [Full Version] [Camera-Ready] [Code] [Poster]

• Mengyi Yan, Yaoshu Wang, Xiaohan Jiang, Haoyi Zhou, Jianxin Li*,
  Towards uncertainty-calibrated structural data enrichment with large language model for few-shot entity resolution,
  Frontiers of Computer Science, 2025 (IF=3.4, JCR Q1) [Paper] [Highlight]

• Yaoshu Wang, Mengyi Yan*, Wei Wang
  PUER: Boosting Few-shot Positive-Unlabeled Entity Resolution with Reinforcement Learning,
  EMNLP 2025(Finding Paper, CCF-B) [Paper] [Supplementary] [Code]

2024

• Mengyi Yan, Wenfei Fan, Yaoshu Wang, Min Xie*,
  Enriching Relations with Additional Attributes for ER,
  The 50th International Conference on Very Large Data Bases (VLDB 2024, CCF-A) [Paper] [Full Version] [Code]

• Mengyi Yan, Yaoshu Wang*, Kehan Pang, Min Xie, Jianxin Li*,
  Efficient Mixture of Experts based on Large Language Models for Low-Resource Data Preprocessing,
  The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2024, CCF-A) [Paper] [Code] [Poster] [Slide]

• Mengyi Yan, Weilong Ren*, Yaoshu Wang, Jianxin Li*,
  A Retrieval-Augmented Framework for Tabular Interpretation with Large Language Model,
  The 29th International Conference on Database Systems for Advanced Applications (DASFAA 2024, CCF-B) [Paper] [Poster] [Slide]

• Wenfei Fan, Ziyan Han, Weilong Ren*, Ding Wang, Yaoshu Wang, Min Xie, Mengyi Yan,
  Splitting Tuples of Mismatched Entities+,
  The 2024 ACM Conference on Management of Data (SIGMOD 2024, CCF-A) [Paper] [Code] [Poster] [Slide]

• Yaoshu Wang, Mengyi Yan,
  Unsupervised Domain Adaptation for Entity Blocking Leveraging Large Language Models,
  The 12th IEEE International Conference on Big Data (BigData 2024, CCF-C) [Paper] [Code]

2023

• Haoyi Zhou, Jianxin Li*, Shanghang Ji, Shuai Zhang, Mengyi Yan, Hui Xiong,
  Expanding the Prediction Capacity in Long Sequence Time-Series Forecasting,
  Artificial Intelligence Journal(IF=4.6, CCF-A, the extension journal version of AAAI'21 Best Paper Informer) [Paper]

2017

• Shuai Zhang, Jianxin Li, Pengtao Xie, Yingchun Zhang, Minglai Shao, Haoyi Zhou, Mengyi Yan,
  Stacked kernel network,
  arXiv preprint arXiv:1711.09219 [Paper]