# LLMAuditor: A Framework for Auditing Large Language Models Using Human-in-the-Loop

arXiv: https://arxiv.org/abs/2402.09346 · HTML: https://mlsanity.com/paper/2402.09346/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 50 references that are in the map.
- First posted on arXiv 14 Feb 2024.

## Builds on (most cited first, 23 of 23)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only](https://mlsanity.com/paper/2306.01116/) (2023)
- [DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models](https://mlsanity.com/paper/2306.11698/) (2023)
- [The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientation](https://mlsanity.com/paper/2301.01768/) (2023)
- [LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples](https://mlsanity.com/paper/2310.01469/) (2023)
- [Evaluating the Factual Consistency of Large Language Models Through News Summarization](https://mlsanity.com/paper/2211.08412/) (2022)
- [Mitigating Political Bias in Language Models Through Reinforced Calibration](https://mlsanity.com/paper/2104.14795/) (2021)
- [The Self-Perception and Political Biases of ChatGPT](https://mlsanity.com/paper/2304.07333/) (2023)
- [LLM-Assisted Content Analysis: Using Large Language Models to Support Deductive Coding](https://mlsanity.com/paper/2306.14924/) (2023)
- [Large Language Models Help Humans Verify Truthfulness -- Except When They Are Convincingly Wrong](https://mlsanity.com/paper/2310.12558/) (2023)
- [Supporting Human-AI Collaboration in Auditing LLMs with LLMs](https://mlsanity.com/paper/2304.09991/) (2023)
- [DelucionQA: Detecting Hallucinations in Domain-specific Question Answering](https://mlsanity.com/paper/2312.05200/) (2023)
- [A New Benchmark and Reverse Validation Method for Passage-level Hallucination Detection](https://mlsanity.com/paper/2310.06498/) (2023)
- [Multiple-Choice Question Generation: Towards an Automated Assessment Framework](https://mlsanity.com/paper/2209.11830/) (2022)
- [ALLURE: Auditing and Improving LLM-based Evaluation of Text using Iterative In-Context-Learning](https://mlsanity.com/paper/2309.13701/) (2023)
- [Shaping the Emerging Norms of Using Large Language Models in Social Computing Research](https://mlsanity.com/paper/2307.04280/) (2023)
- [From Prompt Engineering to Prompt Science With Human in the Loop](https://mlsanity.com/paper/2401.04122/) (2024)

## Built on by (most cited first, 8 of 8)

- [A Systematization of Security Vulnerabilities in Computer Use Agents](https://mlsanity.com/paper/2507.05445/) (2025)
- [STRUCTSENSE: A Task-Agnostic Agentic Framework for Structured Information Extraction with Human-In-The-Loop Evaluation and Benchmarking](https://mlsanity.com/paper/2507.03674/) (2025)
- [Human-In-The-Loop Machine Learning for Safe and Ethical Autonomous Vehicles: Principles, Challenges, and Opportunities](https://mlsanity.com/paper/2408.12548/) (2024)
- [Audited Reasoning Refinement: Fine-Tuning Language Models via LLM-Guided Step-Wise Evaluation and Correction](https://mlsanity.com/paper/2509.12476/) (2025)
- [SOCIA-Nabla: Textual Gradient Meets Multi-Agent Orchestration for Automated Simulator Generation](https://mlsanity.com/paper/2510.18551/) (2025)
- [AuditCopilot: Leveraging LLMs for Fraud Detection in Double-Entry Bookkeeping](https://mlsanity.com/paper/2512.02726/) (2025)
- [From Automation to Collaboration: Human-in-the-Loop Methods for Safe and Trustworthy NLP](https://mlsanity.com/paper/2605.25226/) (2026)
- [IntelliAudit: Using Large Language Models to Evaluate Audit Controls](https://mlsanity.com/paper/2608.07688/) (2026)

## Abstract (arXiv)

As Large Language Models (LLMs) become more pervasive across various users and scenarios, identifying potential issues when using these models becomes essential. Examples of such issues include: bias, inconsistencies, and hallucination. Although auditing the LLM for these problems is often warranted, such a process is neither easy nor accessible for most. An effective method is to probe the LLM using different versions of the same question. This could expose inconsistencies in its knowledge or operation, indicating potential for bias or hallucination. However, to operationalize this auditing method at scale, we need an approach to create those probes reliably and automatically. In this paper we propose the LLMAuditor framework which is an automatic, and scalable solution, where one uses a different LLM along with human-in-the-loop (HIL). This approach offers verifiability and transparency, while avoiding circular reliance on the same LLM, and increasing scientific rigor and generalizability. Specifically, LLMAuditor includes two phases of verification using humans: standardized evaluation criteria to verify responses, and a structured prompt template to generate desired probes. A case study using questions from the TruthfulQA dataset demonstrates that we can generate a reliable set of probes from one LLM that can be used to audit inconsistencies in a different LLM. This process is enhanced by our structured prompt template with HIL, which not only boosts the reliability of our approach in auditing but also yields the delivery of less hallucinated results. The novelty of our research stems from the development of a comprehensive, general-purpose framework that includes a HIL verified prompt template for auditing responses generated by LLMs.