Making Prompts First-Class Citizens for Adaptive LLM Pipelines
Summary: Proposes SPEAR, treating prompts as first-class, structured, versioned artifacts integrated into execution for provenance, introspection, and reuse. Adds adaptive prompt refinement and policy-driven when‑then control to evolve prompts at runtime, unlocking optimization and integration opportunities in LLM pipelines. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Uğur Çetintemel
- 2. Shu Chen
- 3. Alexander W. Lee
- 4. Deepti Raghavan
- 5. Duo Lu
- 6. Andrew Crotty
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 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 |
|---|---|---|---|---|
| 1,963 | DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing | 2025 | VLDB | 9.929429e-05 |
| 2,106 | Palimpzest: Optimizing AI-Powered Analytics with Declarative Query Processing | 2025 | CIDR | 9.5342543e-05 |
| 3,508 | spade: Synthesizing Data Quality Assertions for Large Language Model Pipelines | 2024 | VLDB | 7.0271496e-05 |
| 5,171 | Abacus: A Cost-Based Optimizer for Semantic Operator Systems | 2026 | VLDB | 5.6464993e-05 |
Previous
Page 1 / 1
Next