Bolt-on, Verifiable Provenance for LLM-Powered Data Processing
Summary: BLIP adds bolt-on, model-agnostic provenance to LLM data processing by finding minimal input subsets that reproduce the original answer. Eight guaranteed strategies, adaptive selection, and multi-provenance support deliver verifiability at near-query cost. (summarized by gpt-5.6-luna on Aug 28 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Yiming Lin (University of California Berkeley)
- 2. Sepanta Zeighami (University of California Berkeley)
- 3. Aditya G. Parameswaran (University of California Berkeley)
BibTeX Citation
@article{lin_vldb26,
title = {{Bolt-on, Verifiable Provenance for LLM-Powered Data Processing}},
author = {Lin, Yiming and Zeighami, Sepanta and Parameswaran, Aditya G.},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {11},
pages = {2992--3005},
doi = {10.14778/3836663.3836668},
url = {https://doi.org/10.14778/3836663.3836668},
year = {2026}
}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 18 of 18 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 9,940 | NLProv: Natural Language Provenance | 2016 | VLDB |
| 2 | 10,878 | Can we trust LLM Self-Explanations for Entity Resolution? | 2026 | VLDB |
| 3 | 501 | Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes | 2024 | VLDB |
| 4 | 11,161 | ScaleLLM: A Technique for Scalable LLM-augmented Data Systems | 2025 | SIGMOD |
| 5 | 622 | On the Provenance of Non-Answers to Queries over Extracted Data | 2008 | VLDB |
| 6 | 8,076 | Provenance-Enabled Explainable AI | 2024 | SIGMOD |
| 7 | 11,061 | LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning | 2026 | VLDB |
| 8 | 3,695 | Revisiting Prompt Engineering via Declarative Crowdsourcing | 2024 | CIDR |
| 9 | 4,687 | Provenance for Natural Language Queries | 2017 | VLDB |
| 10 | 8,997 | Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guarantees | 2026 | SIGMOD |