DAPRO adaptively spends a fixed interaction budget across multi-turn LLM conversations and builds valid lower bounds on time-to-jailbreak, with coverage error scaling as the square root of the mean censoring weight.
Conformal prediction under covariate shift.Advances in neural information processing systems, 32
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 6roles
background 1polarities
background 1representative citing papers
Derives analytical characterizations of the length-optimal training-calibration split ratio for split conformal prediction in general settings and specific regression models.
Proposes Cost-Aware Adaptive Conformal Inference framework providing dual statistical guarantees on long-run violation frequency and cumulative violation cost for runtime assurance in dynamic environments.
OLCP and OLCP-Hedge achieve long-run valid coverage in non-exchangeable online settings with narrower prediction sets by localizing conformal prediction to covariates and selecting bandwidth via online convex optimization.
Branched Normalizing Flow improves conditional coverage robustness of conformal prediction under distribution shift by normalizing test inputs to the calibration distribution and mapping prediction sets back.
A new kernel nonconformity score for multivariate conformal prediction that adapts to residual geometry, provides finite-sample coverage, and achieves convergence rates based on effective kernel rank rather than ambient dimension.
citing papers explorer
-
How Many Iterations to Jailbreak? Dynamic Budget Allocation for Multi-Turn LLM Evaluation
DAPRO adaptively spends a fixed interaction budget across multi-turn LLM conversations and builds valid lower bounds on time-to-jailbreak, with coverage error scaling as the square root of the mean censoring weight.
-
On Optimal Data Splitting for Split Conformal Prediction
Derives analytical characterizations of the length-optimal training-calibration split ratio for split conformal prediction in general settings and specific regression models.
-
Cost-Aware Adaptive Conformal Inference for Runtime Assurance in Dynamic Environments
Proposes Cost-Aware Adaptive Conformal Inference framework providing dual statistical guarantees on long-run violation frequency and cumulative violation cost for runtime assurance in dynamic environments.
-
Online Localized Conformal Prediction
OLCP and OLCP-Hedge achieve long-run valid coverage in non-exchangeable online settings with narrower prediction sets by localizing conformal prediction to covariates and selecting bandwidth via online convex optimization.
-
Robust Conditional Conformal Prediction via Branched Normalizing Flow
Branched Normalizing Flow improves conditional coverage robustness of conformal prediction under distribution shift by normalizing test inputs to the calibration distribution and mapping prediction sets back.
-
A Kernel Nonconformity Score for Multivariate Conformal Prediction
A new kernel nonconformity score for multivariate conformal prediction that adapts to residual geometry, provides finite-sample coverage, and achieves convergence rates based on effective kernel rank rather than ambient dimension.