Poodle: Seamlessly Scaling Down Large Language Models with Just-in-Time Model Replacement
cs.DB, cs.LG
Submitted: 2025-12-05
Updated: 2026-09-17
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification
- FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
- Language Models for Text Classification: Is In-Context Learning Enough?
- Distilling the Knowledge in a Neural Network
- SemBench: A Benchmark for Semantic Query Processing Engines
- A Declarative System for Optimizing AI Workloads
- RouteLLM: Learning to Route LLMs with Preference Data
- Knowledge Distillation in Automated Annotation: Supervised Text Classification with LLM-Generated Training Labels
- Semantic Operators: A Declarative Model for Rich, AI-based Data Processing
Related papers
- Cost-Aware Mixture-of-Experts Coordination for Model Markets
- Amora: Communication-Efficient Private Approximate Nearest Neighbors Search
- Vibe Coding on Trial: Operating Characteristics of Unanimous LLM Juries
- Human-Level Text-to-SQL via Reinforcement Learning on Verified Data, Without Pipeline Engineering
- MetaJoin: Adaptive Join Selections for Heterogeneous Tables
- Bridging Business Intent and Data: A Benchmark for Automatic Relational Data Product Generation