# Auditing large language models: a three-layered approach

arXiv: https://arxiv.org/abs/2302.08500 · HTML: https://mlsanity.com/paper/2302.08500/

## Key facts

- Cited by 137 papers in the map (data through 14 Oct 2026).
- Builds on 127 of its 294 references that are in the map.
- First posted on arXiv 16 Feb 2023.

## Builds on (most cited first, 30 of 127)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems](https://mlsanity.com/paper/1905.00537/) (2019)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)

## Built on by (most cited first, 30 of 137)

- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023)
- [Model evaluation for extreme risks](https://mlsanity.com/paper/2305.15324/) (2023)
- [Personality Traits in Large Language Models](https://mlsanity.com/paper/2307.00184/) (2023)
- [Black-Box Access is Insufficient for Rigorous AI Audits](https://mlsanity.com/paper/2401.14446/) (2024)
- [A Survey of Large Language Models in Medicine: Progress, Application, and Challenge](https://mlsanity.com/paper/2311.05112/) (2023)
- [AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap](https://mlsanity.com/paper/2306.01941/) (2023)
- [Frontier AI Regulation: Managing Emerging Risks to Public Safety](https://mlsanity.com/paper/2307.03718/) (2023)
- [Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback](https://mlsanity.com/paper/2303.05453/) (2023)
- [Visibility into AI Agents](https://mlsanity.com/paper/2401.13138/) (2024)
- [Nicer Than Humans: How do Large Language Models Behave in the Prisoner's Dilemma?](https://mlsanity.com/paper/2406.13605/) (2024)
- [A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures](https://mlsanity.com/paper/2506.19676/) (2025)
- [Do LLMs Possess a Personality? Making the MBTI Test an Amazing Evaluation for Large Language Models](https://mlsanity.com/paper/2307.16180/) (2023)
- [Language Models Resist Alignment: Evidence From Data Compression](https://mlsanity.com/paper/2406.06144/) (2024)
- [Managing extreme AI risks amid rapid progress](https://mlsanity.com/paper/2310.17688/) (2023)
- [Training Data Extraction From Pre-trained Language Models: A Survey](https://mlsanity.com/paper/2305.16157/) (2023)
- [Logits of API-Protected LLMs Leak Proprietary Information](https://mlsanity.com/paper/2403.09539/) (2024)
- [Multilingual != Multicultural: Evaluating Gaps Between Multilingual Capabilities and Cultural Alignment in LLMs](https://mlsanity.com/paper/2502.16534/) (2025)
- [SoK: Memorization in General-Purpose Large Language Models](https://mlsanity.com/paper/2310.18362/) (2023)
- [Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling](https://mlsanity.com/paper/2403.01251/) (2024)
- [Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models](https://mlsanity.com/paper/2409.00598/) (2024)
- [Using Large Language Models to Generate, Validate, and Apply User Intent Taxonomies](https://mlsanity.com/paper/2309.13063/) (2023)
- [Open-Sourcing Highly Capable Foundation Models: An evaluation of risks, benefits, and alternative methods for pursuing open-source objectives](https://mlsanity.com/paper/2311.09227/) (2023)
- [Assessing Language Model Deployment with Risk Cards](https://mlsanity.com/paper/2303.18190/) (2023)
- [Navigating LLM Ethics: Advancements, Challenges, and Future Directions](https://mlsanity.com/paper/2406.18841/) (2024)
- [Exploring the Roles of Large Language Models in Reshaping Transportation Systems: A Survey, Framework, and Roadmap](https://mlsanity.com/paper/2503.21411/) (2025)
- [Accuracy and Political Bias of News Source Credibility Ratings by Large Language Models](https://mlsanity.com/paper/2304.00228/) (2023)
- [Causality for Large Language Models](https://mlsanity.com/paper/2410.15319/) (2024)
- [The Model Openness Framework: Promoting Completeness and Openness for Reproducibility, Transparency, and Usability in Artificial Intelligence](https://mlsanity.com/paper/2403.13784/) (2024)
- [Towards Trustworthy AI: A Review of Ethical and Robust Large Language Models](https://mlsanity.com/paper/2407.13934/) (2024)

## Abstract (arXiv)

Large language models (LLMs) represent a major advance in artificial intelligence (AI) research. However, the widespread use of LLMs is also coupled with significant ethical and social challenges. Previous research has pointed towards auditing as a promising governance mechanism to help ensure that AI systems are designed and deployed in ways that are ethical, legal, and technically robust. However, existing auditing procedures fail to address the governance challenges posed by LLMs, which display emergent capabilities and are adaptable to a wide range of downstream tasks. In this article, we address that gap by outlining a novel blueprint for how to audit LLMs. Specifically, we propose a three-layered approach, whereby governance audits (of technology providers that design and disseminate LLMs), model audits (of LLMs after pre-training but prior to their release), and application audits (of applications based on LLMs) complement and inform each other. We show how audits, when conducted in a structured and coordinated manner on all three levels, can be a feasible and effective mechanism for identifying and managing some of the ethical and social risks posed by LLMs. However, it is important to remain realistic about what auditing can reasonably be expected to achieve. Therefore, we discuss the limitations not only of our three-layered approach but also of the prospect of auditing LLMs at all. Ultimately, this article seeks to expand the methodological toolkit available to technology providers and policymakers who wish to analyse and evaluate LLMs from technical, ethical, and legal perspectives.