DBScholar

Back to papers

SemDistill: Bootstrapping a Low-Latency, Low-Cost Semantic Table Annotator from Noisy LLM

Summary: SemDistill distills noisy LLM predictions for table annotation into fast, private local models using scarce trusted labels. It corrects global ontological drift and identifies high-confidence hallucinations via reliability-tiered training, outperforming its teacher at 3,800× lower cost and 2,600× lower latency. (summarized by gpt-6-luna on Oct 22 2026)

Paper ID
he57dd587e8838f78
Venue
SIGMOD
Year
2027
Pagerank
4.9605343e-05
Overall Rank
10,409 | 30.23%
DOI
10.1145/3837124
PDF
Download (CC BY 4.0)

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

BibTeX Citation

@inproceedings{ge_sigmod27,
        title = {{SemDistill: Bootstrapping a Low-Latency, Low-Cost Semantic Table Annotator from Noisy LLM}},
        author = {Ge, Yuhang and Ye, Zhangyan and Mao, Yuren and Gao, Yunjun},
        series = {{SIGMOD} '27},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3837124},
        url = {https://dl.acm.org/doi/10.1145/3837124},
        year = {2027}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank Citing Paper Year Venue Pagerank
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 15 of 15 cited papers.

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

Rank Cited Paper Year Venue Pagerank
100 HoloClean: Holistic Data Repairs with Probabilistic Inference 2017 VLDB 0.00033951027
200 Snorkel: Rapid Training Data Creation with Weak Supervision 2018 VLDB 0.00025443474
366 TURL: Table Understanding through Representation Learning 2021 VLDB 0.00019902067
1,669 Table-GPT: Table Fine-tuned GPT for Diverse Table Tasks 2024 SIGMOD 9.9157758e-05
1,690 Annotating Columns with Pre-trained Language Models 2022 SIGMOD 9.8426663e-05
1,742 Semantics-aware Dataset Discovery from Data Lakes with Contextualized Column-based Representation Learning 2023 VLDB 9.7283207e-05
1,838 CHORUS: Foundation Models for Unified Data Discovery and Exploration 2024 VLDB 9.5195856e-05
1,985 Sato: Contextual Semantic Type Detection in Tables 2020 VLDB 9.2378767e-05
2,334 GitTables: A Large-Scale Corpus of Relational Tables 2023 SIGMOD 8.6058607e-05
3,166 Unicorn: A Unified Multi-tasking Model for Supporting Matching Tasks in Data Integration 2023 SIGMOD 7.5597853e-05
4,335 ArcheType: A Novel Framework for Open-Source Column Type Annotation using Large Language Models 2024 VLDB 6.6432811e-05
7,787 RECA: Related Tables Enhanced Column Semantic Type Annotation Framework 2023 VLDB 5.4356666e-05
8,161 Watchog: A Light-weight Contrastive Learning based Framework for Column Annotation 2023 SIGMOD 5.37207e-05
9,201 Cents: A Flexible and Cost-Effective Framework for LLM-Based Table Understanding 2025 VLDB 5.1950133e-05
9,838 Retrieve-and-Verify: A Table Context Selection Framework for Accurate Column Annotations 2026 SIGMOD 5.1064323e-05
Previous Page 1 / 1 Next

Semantically Similar Papers