# Prediction-Powered Risk Monitoring of Deployed Models for Detecting Harmful Distribution Shifts

Source: [Prediction-Powered Risk Monitoring of Deployed Models for Detecting Harmful Distribution Shifts](<https://www.sota2.com/research/paper/698181afa8b01e76cc8e27e3>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-12T05:00:14.585Z

Authors: Guangyi Zhang, Yunlong Cai, Guanding Yu, Osvaldo Simeone

Published: 2026-02-02T15:32:14.000Z

## Abstract

We study the problem of monitoring model performance in dynamic environments where labeled data are limited. To this end, we propose prediction-powered risk monitoring (PPRM), a semi-supervised risk-monitoring approach based on prediction-powered inference (PPI). PPRM constructs anytime-valid lower bounds on the running risk by combining synthetic labels with a small set of true labels. Harmful shifts are detected via a threshold-based comparison with an upper bound on the nominal risk, satisfying assumption-free finite-sample guarantees on the type-I error. We demonstrate the effectiveness of PPRM through extensive experiments on image classification, large language model (LLM), and telecommunications monitoring tasks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2602.02229>)

[PDF](<https://arxiv.org/pdf/2602.02229.pdf>)