Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guarantees

Summary: Targets LLM cascade cost-quality tradeoffs by provable selection of when to use cheaper LLMs for record processing, addressing weak quality estimation in prior confidence-based cascades. BARGAIN uses adaptive sampling and statistical estimation tuned to data/task to give tight theoretical guarantees (accuracy/precision/recall) and empirically reduces cost up to 86% vs. state-of-the-art. (summarized by gpt-5-mini on Feb 11 2026)

Paper ID: h0b08d826353bd4cb
Venue: SIGMOD
Year: 2026
Pagerank: 5.2410834e-05
Overall Rank: 8,997 | 39.51%
DOI: 10.1145/3769776

Incoming Non-self Citations Over Time

Authors

1. Sepanta Zeighami (University of California Berkeley)
2. Shreya Shankar (University of California Berkeley)
3. Aditya Parameswaran (University of California Berkeley)

BibTeX Citation

@inproceedings{zeighami_sigmod26,
        title = {{Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guarantees}},
        author = {Zeighami, Sepanta and Shankar, Shreya and Parameswaran, Aditya},
        series = {{SIGMOD} '26},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3769776},
        url = {https://dl.acm.org/doi/10.1145/3769776},
        year = {2026}
}

Incoming Citations (Sorted by Pagerank)

Showing 4 of 4 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
6,886	Multi-Objective Agentic Rewrites for Unstructured Data Processing	2026	VLDB	5.6551172e-05
10,415	Automated Discovery of Test Oracles for Database Management Systems Using LLMs	2026	SIGMOD	4.9793485e-05
10,498	ScaleDoc: Scaling LLM-based Predicates over Large Document Collections	2026	SIGMOD	4.9793485e-05
10,845	Featurized-Decomposition Join: Low-Cost Semantic Joins with Guarantees	2026	VLDB	4.9793485e-05

Outgoing Citations (Sorted by Pagerank)

Showing 22 of 22 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
271	NoScope: Optimizing Neural Network Queries over Video at Scale	2017	VLDB	0.00022560564
281	Accelerating Machine Learning Inference with Probabilistic Predicates	2018	SIGMOD	0.00022295232
329	Can Foundation Models Wrangle Your Data?	2023	VLDB	0.00020858443
501	Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes	2024	VLDB	0.00017267905
541	BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analytics	2020	VLDB	0.00016657685
669	CAESURA: Language Models as Multi-Modal Query Planners	2024	CIDR	0.0001495987
683	DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing	2025	VLDB	0.00014817539
2,341	The Design of an LLM-powered Unstructured Analytics System	2025	CIDR	8.6066183e-05
2,776	Approximate Selection with Guarantees using Proxies	2020	VLDB	8.0309448e-05
3,250	How Large Language Models Will Disrupt Data Management	2023	VLDB	7.4938546e-05
3,650	TASTI: Semantic Indexes for Machine Learning-based Queries over Unstructured Data	2022	SIGMOD	7.1341771e-05
3,874	Accelerating Approximate Aggregation Queries with Expensive Predicates	2021	VLDB	6.953738e-05
3,884	FiGO: Fine-Grained Query Optimization in Video Analytics	2022	SIGMOD	6.948464e-05
3,948	OTIF: Efficient Tracker Pre-processing over Large Video Datasets	2022	SIGMOD	6.9053923e-05
3,973	RetClean: Retrieval-Based Data Cleaning Using LLMs and Data Lakes	2024	VLDB	6.8876964e-05
4,142	AOP: Automated and Interactive LLM Pipeline Orchestration for Answering Complex Queries	2025	CIDR	6.7814795e-05
5,410	ELEET: Efficient Learned Query Execution over Text and Tables	2024	VLDB	6.1408676e-05
5,911	On Efficient Approximate Queries over Machine Learning Models	2023	VLDB	5.9501384e-05
6,993	Solo: Data Discovery Using Natural Language Questions Via A Self-Supervised Approach	2023	SIGMOD	5.626765e-05
7,801	Accelerating Aggregation Queries on Unstructured Streams of Data	2023	VLDB	5.4507311e-05
7,885	Semantic Integrity Constraints: Declarative Guardrails for AI-Augmented Data Processing Systems	2025	VLDB	5.433531e-05
8,316	ThriftLLM: On Cost-Effective Selection of Large Language Models for Classification Queries	2025	VLDB	5.3561732e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	10,841	Bolt-on, Verifiable Provenance for LLM-Powered Data Processing	2026	VLDB
2	3,695	Revisiting Prompt Engineering via Declarative Crowdsourcing	2024	CIDR
3	11,061	LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning	2026	VLDB
4	5,149	LLM for Data Management	2024	VLDB
5	10,765	LLMs as Stratification Signals for KG Accuracy Evaluation	2026	VLDB
6	11,161	ScaleLLM: A Technique for Scalable LLM-augmented Data Systems	2025	SIGMOD
7	6,860	SpareLLM: Automatically Selecting Task-Specific Minimum-Cost Large Language Models under Equivalence Constraint	2025	SIGMOD
8	10,690	Task Cascades for Efficient Unstructured Data Processing	2026	SIGMOD
9	8,888	Optimized Batch Prompting for Cost-effective LLMs	2025	VLDB
10	8,316	ThriftLLM: On Cost-Effective Selection of Large Language Models for Classification Queries	2025	VLDB