Uncertainty-Aware Sequential Decision Rules for Event-Triggered LLM Invocation in Streaming Systems
Zhaohui Wang
cs.LG, cs.AI, stat.ML
Submitted: 2026-06-27
Comments: 18 pages, 5 figures. Accepted to the ECML PKDD 2026 Research Track
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
- Adaptive Computation Time for Recurrent Neural Networks
- Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
- RouteLLM: Learning to Route LLMs with Preference Data
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks