Editorial
CrossVerify: low-payload external validation signals for heterogeneous black-box LLM cascades
@ARTICLE{10.4108/eetsis.14497, author={Li Luo and Keng Yap Ng and Wei Chong Choo}, title={CrossVerify: low-payload external validation signals for heterogeneous black-box LLM cascades}, journal={EAI Endorsed Transactions on Scalable Information Systems}, volume={13}, number={3}, publisher={EAI}, journal_a={SIS}, year={2026}, month={9}, keywords={LLM cascade, cross-verification, black-box routing, selective prediction, confidence calibration}, doi={10.4108/eetsis.14497} }- Li Luo
Keng Yap Ng
Wei Chong Choo
Year: 2026
CrossVerify: low-payload external validation signals for heterogeneous black-box LLM cascades
SIS
EAI
DOI: 10.4108/eetsis.14497
Abstract
INTRODUCTION: Heterogeneous black-box LLM cascades need routing signals that are reliable, calibratable, and computable without hidden-state access. OBJECTIVES: This study evaluates whether external verifier-support signals can complement proposer self-confidence in low-payload cascade routing. METHODS: CrossVerify is designed and tested on six datasets, three proposer-verifier pairs, and five random seeds under both signal-analysis and fixed-fallback escalation settings. RESULTS: Proposer confidence is the strongest average single-feature baseline, while verifier support is the strongest external signal; their combination yields the best overall routing performance, with clear task dependence and a 28-byte black-box-compatible interface. CONCLUSION: CrossVerify offers a deployment-compatible signal design whose main value is complementing self-confidence rather than replacing it.
Copyright © 2026 Li Luo et al., licensed to EAI. This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.