Data Imputation with Limited Data Redundancy Using Data Lakes

Summary: LakeFill leverages LLMs and data lakes for tuple-level retrieval and encoding of incomplete tuples to find cross-table candidates when intra-table redundancy is low. It uses checklist-based reranking and a two-stage confidence-aware reasoner, beating prior methods. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID: he170fa6bfe72bfe3
Venue: VLDB
Year: 2025
Pagerank: 5.4906208e-05
Overall Rank: 7,583 | 49.02%
DOI: 10.14778/3748191.3748200

Incoming Non-self Citations Over Time

Authors

1. Chenyu Yang (Hong Kong University of Science and Technology)
2. Yuyu Luo (Hong Kong University of Science and Technology)
3. Chuanxuan Cui (Renmin University of China)
4. Ju Fan (Renmin University of China)
5. Chengliang Chai (Beijing Institute of Technology)
6. Nan Tang (Hong Kong University of Science and Technology)

BibTeX Citation

@article{yang_vldb25,
        title = {{Data Imputation with Limited Data Redundancy Using Data Lakes}},
        author = {Yang, Chenyu and Luo, Yuyu and Cui, Chuanxuan and Fan, Ju and Chai, Chengliang and Tang, Nan},
        journal = {PVLDB},
        series = {{VLDB} '25},
        volume = {18},
        number = {10},
        pages = {3354--3367},
        doi = {10.14778/3748191.3748200},
        url = {https://doi.org/10.14778/3748191.3748200},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 4 of 4 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
7,090	LEAD: Iterative Data Selection for Efficient LLM Instruction Tuning	2026	VLDB	5.601767e-05
10,352	Towards Scalable Visual Data Wrangling via Direct Manipulation	2026	CIDR	4.9793485e-05
10,853	Auto-Fill: Learning to Predict Missing Values Accurately with Specialist Language Models	2026	VLDB	4.9793485e-05
11,034	Data Agents: Rethinking Data Systems in the AI Agent Era	2026	VLDB	4.9793485e-05

Outgoing Citations (Sorted by Pagerank)

Showing 14 of 14 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
104	HoloClean: Holistic Data Repairs with Probabilistic Inference	2017	VLDB	0.00033690989
134	Deep Entity Matching with Pre-Trained Language Models	2021	VLDB	0.00030043481
329	Can Foundation Models Wrangle Your Data?	2023	VLDB	0.00020858443
377	TURL: Table Understanding through Representation Learning	2021	VLDB	0.00019570264
989	Towards Certain Fixes with Editing Rules and Master Data	2010	VLDB	0.0001265344
1,099	KATARA: A Data Cleaning System Powered by Knowledge Bases and Crowdsourcing	2015	SIGMOD	0.00012037058
1,342	Baran: Effective Error Correction via a Unified Context Representation and Transfer Learning	2020	VLDB	0.00010968223
1,344	Detecting Data Errors: Where are we and what needs to be done?	2016	VLDB	0.00010956518
1,978	Table-GPT: Table Fine-tuned GPT for Diverse Table Tasks	2024	SIGMOD	9.2730152e-05
1,991	RPT: Relational Pre-trained Transformer Is Almost All You Need towards Democratizing Data Preparation	2021	VLDB	9.2383849e-05
2,348	The Dawn of Natural Language to SQL: Are We Fully Ready?	2024	VLDB	8.6009821e-05
5,495	HAIChart: Human and AI Paired Visualization System	2024	VLDB	6.1056297e-05
7,258	Learned Data-aware Image Representations of Line Charts for Similarity Search	2023	SIGMOD	5.572114e-05
9,311	VerifAI: Verified Generative AI	2024	CIDR	5.1965878e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	501	Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes	2024	VLDB
2	3,973	RetClean: Retrieval-Based Data Cleaning Using LLMs and Data Lakes	2024	VLDB
3	11,403	TARImpute: Task-Aware auto-Recommender System for Missing Value Imputation Algorithms with Clustering Case Studies	2025	VLDB
4	11,514	Certain and Approximately Certain Models for Statistical Learning	2024	SIGMOD
5	3,441	Efficient and Effective Data Imputation with Influence Functions	2022	VLDB
6	2,239	Query Optimization for Dynamic Imputation	2017	VLDB
7	5,278	Enriching Data Imputation with Extensive Similarity Neighbors	2015	VLDB
8	10,181	In-Database Data Imputation	2024	SIGMOD
9	10,853	Auto-Fill: Learning to Predict Missing Values Accurately with Specialist Language Models	2026	VLDB
10	8,420	On LLM-Enhanced Mixed-Type Data Imputation with High-Order Message Passing	2025	VLDB