# AI Evaluation Should Measure Verification Cost, Not Correctness Alone

arXiv: https://arxiv.org/abs/2608.08709 · HTML: https://mlsanity.com/paper/2608.08709/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 36 references that are in the map.
- First posted on arXiv 9 Aug 2026.

## Builds on (most cited first, 25 of 25)

- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [PAL: Program-aided Language Models](https://mlsanity.com/paper/2211.10435/) (2022)
- [Dynabench: Rethinking Benchmarking in NLP](https://mlsanity.com/paper/2104.14337/) (2021)
- [How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering](https://mlsanity.com/paper/2012.00955/) (2020)
- [Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance](https://mlsanity.com/paper/2006.14779/) (2020)
- [HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models](https://mlsanity.com/paper/2305.11747/) (2023)
- [Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning](https://mlsanity.com/paper/2205.09712/) (2022)
- [Faithful Chain-of-Thought Reasoning](https://mlsanity.com/paper/2301.13379/) (2023)
- [Do Large Language Models Know What They Don't Know?](https://mlsanity.com/paper/2305.18153/) (2023)
- [Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools](https://mlsanity.com/paper/2405.20362/) (2024)
- [Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models](https://mlsanity.com/paper/2401.01301/) (2024)
- [Investigating Data Contamination in Modern Benchmarks for Large Language Models](https://mlsanity.com/paper/2311.09783/) (2023)
- [Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity](https://mlsanity.com/paper/2507.09089/) (2025)
- [Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation](https://mlsanity.com/paper/2510.11977/) (2025)
- [Towards a Science of AI Agent Reliability](https://mlsanity.com/paper/2602.16666/) (2026)
- [Beyond Accuracy: A Multi-Dimensional Framework for Evaluating Enterprise Agentic AI Systems](https://mlsanity.com/paper/2511.14136/) (2025)

## Abstract (arXiv)

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.