AI Evaluation Should Measure Verification Cost, Not Correctness Alone

arXiv:2608.08709 · cs.AI, cs.SE · Submitted 2026-08-09 · Read on arXiv

Viviana Crescitelli, Generoso Immediato, Fabio Persia, Stefania Costantini

cs.AI, cs.SE

Submitted: 2026-08-09

Updated: 2026-08-11

Comments: 20 pages, 1 table

License: http://creativecommons.org/licenses/by-nc-nd/4.0/

The gist: The reliability of AI generative models is typically measured by output correctness, yet in practice it depends on the effort required to verify those outputs.

Terminology

Abstract

The reliability of AI generative models is typically measured by output correctness, yet in practice it depends on the effort required to verify those outputs. We argue that current evaluation metrics overlook a critical failure mode: Verification-Cost Errors (VCEs), defined as incorrect input-output pairs that a declared fraction of the verifier population fails to identify within the verification budget available in a given deployment context. Unlike standard notions of "hallucination", VCEs are defined operationally, by the failure of correct identification within budget rather than by any property of the output itself. Plausibility and authoritative presentation are hypothesised contributors to that failure, not defining conditions. To capture this asymmetry, we introduce the notion of verification cost relative to a deployment budget as an operational dimension that current evaluation does not routinely capture. The quantity is presented as a conceptual instrument rather than a finalized metric. Evidence from code generation and multi-modal document understanding shows that high benchmark accuracy can mask significant verification effort in practice. We therefore take the position that correctness alone is insufficient as a measure of reliability. AI evaluation should explicitly account for verification cost, reflecting whether errors can be detected under realistic resource constraints.

Sources

Related papers