Revisiting Prompt Engineering via Declarative Crowdsourcing

Summary: Treats LLMs as crowd workers and introduces declarative prompt engineering: applying declarative crowdsourcing concepts—multiple prompting strategies, consistency checks, and hybrid LLM/non‑LLM pipelines—to make prompt design systematic and cost-aware. Validated on sorting, entity resolution, and imputation. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID: 526
Venue: CIDR
Year: 2024
Pagerank: 6.9368666e-05
Overall Rank: 4,050 | 72.22%
DOI: -

Incoming Non-self Citations Over Time

Authors

1. Aditya G. Parameswaran (University of California Berkeley)
2. Shreya Shankar (University of California Berkeley)
3. Parth Asawa (University of California Berkeley)
4. Naman Jain (University of California Berkeley)
5. Yujie Wang (University of California Berkeley)

BibTeX Citation

@inproceedings{parameswaran_cidr24,
        address = {Amsterdam, Netherlands},
        series = {{CIDR} '24},
        title = {{Revisiting Prompt Engineering via Declarative Crowdsourcing}},
        booktitle = {Proceedings of the {Conference} on {Innovative} {Data} {Systems} {Research}},
        author = {Parameswaran, Aditya G. and Shankar, Shreya and Asawa, Parth and Jain, Naman and Wang, Yujie},
        year = {2024}
}

Incoming Citations (Sorted by Pagerank)

Showing 5 of 5 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
1,245	Palimpzest: Optimizing AI-Powered Analytics with Declarative Query Processing	2025	CIDR	0.00011507415
1,343	DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing	2025	VLDB	0.00011095866
4,621	spade: Synthesizing Data Quality Assertions for Large Language Model Pipelines	2024	VLDB	6.6024412e-05
4,944	Hybrid Querying Over Relational Databases and Large Language Models	2025	CIDR	6.432467e-05
6,211	GenEdit: Compounding Operators and Continuous Improvement to Tackle Text-to-SQL in the Enterprise	2025	CIDR	5.9425753e-05

Outgoing Citations (Sorted by Pagerank)

Showing 10 of 10 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
90	CrowdDB: Answering Queries with Crowdsourcing	2011	SIGMOD	0.00034951786
196	CrowdER: Crowdsourcing Entity Resolution	2012	VLDB	0.00025780596
248	Evaluation of entity resolution approaches on real-world match problems	2010	VLDB	0.00023278354
251	Crowdsourced Databases: Query Processing with People	2011	CIDR	0.00023261113
265	Human-powered Sorts and Joins	2012	VLDB	0.00022935368
420	Can Foundation Models Wrangle Your Data?	2023	VLDB	0.00018789852
743	So Who Won? Dynamic Max Discovery with the Crowd	2012	SIGMOD	0.00014421358
852	Leveraging Transitive Relations for Crowdsourced Joins	2013	SIGMOD	0.00013604253
997	CrowdScreen: Algorithms for Filtering Data with Humans	2012	SIGMOD	0.00012755983
1,910	Counting with the Crowd	2013	VLDB	9.4972788e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	713	Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes	2024	VLDB
2	9,293	Intelligent Agents for Data Exploration	2024	VLDB
3	10,614	LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning	2026	VLDB
4	6,101	LLM for Data Management	2024	VLDB
5	8,829	Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guarantees	2026	SIGMOD
6	10,318	In-context Clustering-based Entity Resolution with Large Language Models: A Design Space Exploration	2026	SIGMOD
7	10,132	Making Prompts First-Class Citizens for Adaptive LLM Pipelines	2026	CIDR
8	8,906	Unveiling Challenges for LLMs in Enterprise Data Engineering	2026	VLDB
9	13,311	Prompt Editor: A Taxonomy-driven System for Guided LLM Prompt Development in Enterprise Settings	2025	SIGMOD
10	10,856	Optimized Batch Prompting for Cost-effective LLMs	2025	VLDB