No article text was recorded for this version.
uncertainty-based model routing
Version 1 of 171 papers92 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Optimising Calls to Large Language Models with Uncertainty-Based Two-Tier Selection
- Blog: Emergent Wisdom at BEA 2025 Shared Task: From Lexical Understanding to Reflective Reasoning for Pedagogical Ability Assessment
- Blog: UnfoldML: Cost-Aware and Uncertainty-Based Dynamic 2D Prediction for Multi-Stage Classification
- Blog: Efficient Twin Migration in Vehicular Metaverses: Multi-Agent Split Deep Reinforcement Learning with Spatio-Temporal Trajectory Generation
- Blog: Tiny Models are the Computational Saver for Large Models
- Blog: Margin-Adaptive Confidence Ranking for Reliable LLM Judgement
- Blog: CICLe: Conformal In-Context Learning for Largescale Multi-Class Food Risk Classification
- Blog: Intent Detection in the Age of LLMs
- Blog: Crayon: Customized On-Device LLM via Instant Adapter Blending and Edge-Server Hybrid Inference
- Blog: Leveraging Uncertainty Estimation for Efficient LLM Routing
- Blog: Learning Word-Level Confidence For Subword End-to-End ASR
- Blog: SafeGround: Know When to Trust GUI Grounding Models via Uncertainty Calibration
- Blog: Adaptive Multi-state Pipe Framework Based on Set Pair Analysis
- Blog: Division-of-Thoughts: Harnessing Hybrid Language Model Synergy for Efficient On-Device Agents
- Blog: On Bits and Bandits: Quantifying the Regret-Information Trade-off
- Blog: TAPS: Task Aware Proposal Distributions for Speculative Sampling
- Blog: Towards an On-device Agent for Text Rewriting
- Blog: Complexity-aware Adaptive Training and Inference for Edge-Cloud Distributed AI Systems
- Blog: Selective Explanations
- Blog: Speeding Up Image Classifiers with Little Companions
- Blog: Uncertainty Sets for Image Classifiers using Conformal Prediction
- Blog: Distilling BlackBox to Interpretable models for Efficient Transfer Learning
- Blog: Two Wrongs Can Make a Right: A Transfer Learning Approach for Chemical Discovery with Chemical Accuracy
- Blog: Uncertainty-Guided Enhancement on Driving Perception System via Foundation Models
- Blog: Ask a Strong LLM Judge when Your Reward Model is Uncertain
- Blog: Conformal Arbitrage: Risk-Controlled Balancing of Competing Objectives in Language Models
- Blog: On Cost-Effective LLM-as-a-Judge Improvement Techniques
- Blog: Overcoming Heterogeneous Data in Federated Medical Vision-Language Pre-training: A Triple-Embedding Model Selector Approach
- Blog: Revisiting Prompt Engineering via Declarative Crowdsourcing
- Blog: ConfTuner: Training Large Language Models to Express Their Confidence Verbally
- Blog: Anytime Safe PAC Efficient Reasoning
- Blog: Calibrating Long-form Generations From Large Language Models
- Blog: Data Shunt: Collaboration of Small and Large Models for Lower Costs and Better Performance
- Blog: Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!
- Blog: KnowProxy: Adapting Large Language Models by Knowledge-guided Proxy
- Blog: On the Provable Performance Guarantee of Efficient Reasoning Models
- Blog: Ask a Strong LLM Judge when Your Reward Model is Uncertain
- Blog: Trustworthy Long-Tailed Classification
- Blog: Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas
- Blog: UncertainSAM: Fast and Efficient Uncertainty Quantification of the Segment Anything Model
- Blog: Allocation, Not Volume: Test-Time Compute for Agentic Forecasting
- Blog: Making Pre-trained Language Models both Task-solvers and Self-calibrators
- Blog: STREAQ: Selective Tiered Routing for Effective and Affordable Contact Center Quality Assurance
- Blog: EdgeFM: Leveraging Foundation Model for Open-set Learning on the Edge
- Blog: Resource-efficient In-orbit Detection of Earth Objects
- Blog: ConfTuner: Training Large Language Models to Express Their Confidence Verbally
- Blog: Efficient Out-of-Scope Detection in Dialogue Systems via Uncertainty-Driven LLM Routing
- Blog: Cascading Sum-Product Networks using Robustness
- Blog: The bottlenecks of AI: challenges for embedded and real-time research in a data-centric age
- Blog: Energy-Efficient Uncertainty-Aware Biomass Composition Prediction at the Edge
- Blog: CodeChemist: Test-Time Scaling for Low-Resource Code Generation via Functional Knowledge Transfer
- Blog: Who Knows the Answer? Finding the Best Model and Prompt for Each Query Using Confidence-Based Search
- Blog: Query-Level Uncertainty in Large Language Models
- Blog: PAC Reasoning: Controlling the Performance Loss for Efficient Reasoning
- Blog: In-Context Distillation with Self-Consistency Cascades: A Simple, Training-Free Way to Reduce LLM Agent Costs
- Blog: On Bits and Bandits: Quantifying the Regret-Information Trade-off
- Blog: Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization
- Blog: PRISM: Festina Lente Proactivity—Risk-Sensitive, Uncertainty-Aware Deliberation for Proactive Agents
- Blog: Play to Your Strengths: Collaborative Intelligence of Conventional Recommender Models and Large Language Models
- Blog: When in Doubt, Cascade: Towards Building Efficient and Capable Guardrails
Showing 60 of 71 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_uncertainty_based_model_routing_cb2838fe,
title = {uncertainty-based model routing},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/uncertainty-based-model-routing/rdr_cb2838fe69c04d98af5ca7b9c91c8b2c},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_uncertainty_based_model_routing_cb2838fe_v1,
title = {uncertainty-based model routing},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/uncertainty-based-model-routing/rdr_cb2838fe69c04d98af5ca7b9c91c8b2c/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}