Adaptive RAG systems exhibit a large robustness gap: small surface changes in semantically identical queries cause big shifts in retrieval decisions and answer accuracy.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
PASC converts multi-stage joint coverage into a single scalar conformal problem on the joint max nonconformity score, delivering finite-sample distribution-free guarantees and higher empirical coverage than Bonferroni or independent calibration.
UCCI calibrates LLM uncertainty to error probabilities with isotonic regression for cost-optimal cascade routing, delivering 31% cost savings at maintained accuracy on a 75k-query NER task.
citing papers explorer
-
How You Ask Matters! Adaptive RAG Robustness to Query Variations
Adaptive RAG systems exhibit a large robustness gap: small surface changes in semantically identical queries cause big shifts in retrieval decisions and answer accuracy.
-
PASC: Pipeline-Aware Conformal Prediction with Joint Coverage Guarantees for Multi-Stage NLP and LLM Pipelines
PASC converts multi-stage joint coverage into a single scalar conformal problem on the joint max nonconformity score, delivering finite-sample distribution-free guarantees and higher empirical coverage than Bonferroni or independent calibration.
-
UCCI: Calibrated Uncertainty for Cost-Optimal LLM Cascade Routing
UCCI calibrates LLM uncertainty to error probabilities with isotonic regression for cost-optimal cascade routing, delivering 31% cost savings at maintained accuracy on a 75k-query NER task.