# Beyond Benchmarks: On The False Promise of AI Regulation

arXiv: https://arxiv.org/abs/2501.15693 · HTML: https://mlsanity.com/paper/2501.15693/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 71 references that are in the map.
- First posted on arXiv 26 Jan 2025.

## Builds on (most cited first, 22 of 22)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks](https://mlsanity.com/paper/1702.01135/) (2017)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails](https://mlsanity.com/paper/2310.10501/) (2023)
- [State of What Art? A Call for Multi-Prompt LLM Evaluation](https://mlsanity.com/paper/2401.00595/) (2023)
- [Analysis Methods in Neural Language Processing: A Survey](https://mlsanity.com/paper/1812.08951/) (2018)
- [Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them](https://mlsanity.com/paper/1903.03862/) (2019)
- [Algorithms for Verifying Deep Neural Networks](https://mlsanity.com/paper/1903.06758/) (2019)
- [Does Knowledge Distillation Really Work?](https://mlsanity.com/paper/2106.05945/) (2021)
- [Yin and Yang: Balancing and Answering Binary Visual Questions](https://mlsanity.com/paper/1511.05099/) (2015)
- [A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models](https://mlsanity.com/paper/2402.13457/) (2024)
- [AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policies](https://mlsanity.com/paper/2407.17436/) (2024)
- [Introduction to Neural Network Verification](https://mlsanity.com/paper/2109.10317/) (2021)
- [On the Limitations of Dataset Balancing: The Lost Battle Against Spurious Correlations](https://mlsanity.com/paper/2204.12708/) (2022)
- [NLP Verification: Towards a General Methodology for Certifying Robustness](https://mlsanity.com/paper/2403.10144/) (2024)
- [Evaluating Robustness of Neural Networks with Mixed Integer Programming](https://mlsanity.com/paper/1711.07356/) (2017)

## Built on by (most cited first, 4 of 4)

- [Thinking Beyond Tokens: From Brain-Inspired Intelligence to Cognitive Foundations for Artificial General Intelligence and its Societal Impact](https://mlsanity.com/paper/2507.00951/) (2025)
- [Bounding the Black Box: A Statistical Certification Framework for AI Risk Regulation](https://mlsanity.com/paper/2604.21854/) (2026)
- [From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law](https://mlsanity.com/paper/2506.06391/) (2025)
- [The Normalization of Deviance in AI Development](https://mlsanity.com/paper/2609.05749/) (2026)

## Abstract (arXiv)

The performance of AI models on safety benchmarks does not indicate their real-world performance after deployment. This opaqueness of AI models impedes existing regulatory frameworks constituted on benchmark performance, leaving them incapable of mitigating ongoing real-world harm. The problem stems from a fundamental challenge in AI interpretability, which seems to be overlooked by regulators and decision makers. We propose a simple, realistic and readily usable regulatory framework which does not rely on benchmarks, and call for interdisciplinary collaboration to find new ways to address this crucial problem.