An edge-cloud-expert LLM cascade for telecom knowledge systems minimizes processing cost subject to misalignment-risk bounds via multiple hypothesis testing on knowledge and confidence scores.
Towards a cascaded LLM framework for cost-effective human-AI decision-making
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
Independent aggregation of LLMs reaches 83.43% accuracy on 1,189 KalshiBench questions, 1.01 points above the best single model, while deliberative consensus drops to 76% and error correlations limit further gains.
citing papers explorer
-
Reliable LLM-Based Edge-Cloud-Expert Cascades for Telecom Knowledge Systems
An edge-cloud-expert LLM cascade for telecom knowledge systems minimizes processing cost subject to misalignment-risk bounds via multiple hypothesis testing on knowledge and confidence scores.
-
Design and Evaluation of Multi-Agent AI Oracle Systems for Prediction Market Resolution
Independent aggregation of LLMs reaches 83.43% accuracy on 1,189 KalshiBench questions, 1.01 points above the best single model, while deliberative consensus drops to 76% and error correlations limit further gains.