CAESURA: Language Models as Multi-Modal Query Planners

Summary: Introduces Language-Model-Driven Query Planning: use LMs to translate natural-language queries into executable multi-modal query plans with operators over arbitrary modalities (images, text, video), unlike traditional SQL planners. Presents CAESURA, a GPT-4 prototype demonstrating feasibility on two datasets and proposing techniques to improve LM planning robustness for end-to-end multi-modal query execution. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID: 504
Venue: CIDR
Year: 2024
Pagerank: 0.0001302491
Overall Rank: 950 | 93.49%
DOI: -

Incoming Non-self Citations Over Time

Authors

1. Matthias Urban (Technical University of Darmstadt)
2. Carsten Binnig (German National Research Center for Information Technology; Technical University of Darmstadt)

BibTeX Citation

@inproceedings{urban_cidr24,
        address = {Amsterdam, Netherlands},
        series = {{CIDR} '24},
        title = {{CAESURA: Language Models as Multi-Modal Query Planners}},
        booktitle = {Proceedings of the {Conference} on {Innovative} {Data} {Systems} {Research}},
        author = {Urban, Matthias and Binnig, Carsten},
        year = {2024}
}

Incoming Citations (Sorted by Pagerank)

Showing 25 of 25 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
1,981	ReAcTable: Enhancing ReAct for Table Question Answering	2024	VLDB	9.3579557e-05
2,956	The Design of an LLM-powered Unstructured Analytics System	2025	CIDR	7.9203461e-05
4,045	Logical and Physical Optimizations for SQL Query Execution over Large Language Models	2025	SIGMOD	6.9394654e-05
4,081	Abacus: A Cost-Based Optimizer for Semantic Operator Systems	2026	VLDB	6.9165634e-05
5,220	Databases Unbound: Querying All of the World’s Bytes with AI	2024	VLDB	6.3108362e-05
6,118	ELEET: Efficient Learned Query Execution over Text and Tables	2024	VLDB	5.9698795e-05
6,371	QUEST: Query Optimization in Unstructured Document Analysis	2025	VLDB	5.8962187e-05
7,439	AOP: Automated and Interactive LLM Pipeline Orchestration for Answering Complex Queries	2025	CIDR	5.6181103e-05
7,694	PalimpChat: Declarative and Interactive AI analytics	2025	SIGMOD	5.5661389e-05
7,809	Can Large Language Models Be Query Optimizer for Relational Databases?	2026	SIGMOD	5.5399022e-05
8,829	Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guarantees	2026	SIGMOD	5.3613784e-05
8,868	SemBench: A Benchmark for Semantic Query Processing Engines	2026	VLDB	5.3546848e-05
8,906	Unveiling Challenges for LLMs in Enterprise Data Engineering	2026	VLDB	5.3483178e-05
9,307	Unify: A System For Unstructured Data Analytics	2025	VLDB	5.289545e-05
9,841	Semantic Integrity Constraints: Declarative Guardrails for AI-Augmented Data Processing Systems	2025	VLDB	5.2101877e-05
10,120	KathDB: Explainable Multimodal Database Management System with Human-AI Collaboration	2026	CIDR	5.093636e-05
10,137	Deep Research is the New Analytics System: Towards Building the Runtime for AI-Driven Analytics	2026	CIDR	5.093636e-05
10,140	BridgeScope: A Universal Toolkit for Bridging Large Language Models and Databases	2026	CIDR	5.093636e-05
10,401	SEFRQO: A Self-Evolving Fine-Tuned RAG-Based Query Optimizer	2026	SIGMOD	5.093636e-05
10,433	Beyond Relational: Semantic-Aware Multi-Modal Analytics with LLM-Native Query Optimization	2026	SIGMOD	5.093636e-05
10,501	SQLBarber: A System Leveraging Large Language Models to Generate Customized and Realistic SQL Workloads	2026	SIGMOD	5.093636e-05
10,504	Task Cascades for Efficient Unstructured Data Processing	2026	SIGMOD	5.093636e-05
10,572	Relational Deep Dive: Error-Aware Queries Over Unstructured Data	2026	VLDB	5.093636e-05

Outgoing Citations (Sorted by Pagerank)

Showing 4 of 4 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
1	Access Path Selection in a Relational Database Management System	1979	SIGMOD	0.0024089429
1,550	Symphony: Towards Natural Language Query Answering over Multi-modal Data Lakes	2023	CIDR	0.00010385904
2,175	From Natural Language Processing to Neural Databases	2021	VLDB	9.0215773e-05
2,844	Zero-Shot Cost Models for Out-of-the-box Learned Cost Prediction	2022	VLDB	8.0608767e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	11,028	Smart SPARQL Advisor: Guiding Users in Query Formulation with Performance Prediction	2025	VLDB
2	11,025	A Demonstration of QueryArtisan: Real-Time Data Lake Analysis via Dynamically Generated Data Manipulation Code	2025	VLDB
3	11,120	Welding Natural Language Queries to Analytics IRs with LLMs	2024	CIDR
4	1,550	Symphony: Towards Natural Language Query Answering over Multi-modal Data Lakes	2023	CIDR
5	2,710	OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignment	2025	SIGMOD
6	7,809	Can Large Language Models Be Query Optimizer for Relational Databases?	2026	SIGMOD
7	4,944	Hybrid Querying Over Relational Databases and Large Language Models	2025	CIDR
8	4,308	AutoTQA: Towards Autonomous Tabular Question Answering through Multi-Agent Large Language Models	2024	VLDB
9	8,343	An Interactive Multi-modal Query Answering System with Retrieval-Augmented Large Language Models	2024	VLDB
10	4,045	Logical and Physical Optimizations for SQL Query Execution over Large Language Models	2025	SIGMOD