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.
Thought calibration: Efficient and confident test-time scaling
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
SFT supplies entangled compositional traces of atomic skills and routing modules; RL identifies those modules and enables recombination on novel compositions outside the SFT support.
A wrapper for black-box generate-verify AI pipelines that uses a conservative hard-negative reference pool and e-processes to control the probability of releasing on infeasible tasks while permitting release on feasible ones.
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.
-
From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning
SFT supplies entangled compositional traces of atomic skills and routing modules; RL identifies those modules and enables recombination on novel compositions outside the SFT support.
-
When Should an AI Workflow Release? Always-Valid Inference for Black-Box Generate-Verify Systems
A wrapper for black-box generate-verify AI pipelines that uses a conservative hard-negative reference pool and e-processes to control the probability of releasing on infeasible tasks while permitting release on feasible ones.