# "Oops, Did I Just Say That?" Testing and Repairing Unethical Suggestions of Large Language Models with Suggest-Critique-Reflect Process

arXiv: https://arxiv.org/abs/2305.02626 · HTML: https://mlsanity.com/paper/2305.02626/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 65 references that are in the map.
- First posted on arXiv 4 May 2023.

## Builds on (most cited first, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [GLM-130B: An Open Bilingual Pre-trained Model](https://mlsanity.com/paper/2210.02414/) (2022)
- [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020)
- [Instruction Tuning with GPT-4](https://mlsanity.com/paper/2304.03277/) (2023)
- [AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotators](https://mlsanity.com/paper/2303.16854/) (2023)
- [Can Machines Learn Morality? The Delphi Experiment](https://mlsanity.com/paper/2110.07574/) (2021)
- [ProsocialDialog: A Prosocial Backbone for Conversational Agents](https://mlsanity.com/paper/2205.12688/) (2022)
- [The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems](https://mlsanity.com/paper/2204.03021/) (2022)
- [When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment](https://mlsanity.com/paper/2210.01478/) (2022)
- [Fairness Testing: A Comprehensive Survey and Analysis of Trends](https://mlsanity.com/paper/2207.10223/) (2022)
- [Towards Identifying Social Bias in Dialog Systems: Frame, Datasets, and Benchmarks](https://mlsanity.com/paper/2202.08011/) (2022)
- [Phoenix: Democratizing ChatGPT across Languages](https://mlsanity.com/paper/2304.10453/) (2023)
- [Identifying Implementation Bugs in Machine Learning based Image Classifiers using Metamorphic Testing](https://mlsanity.com/paper/1808.05353/) (2018)

## Built on by (most cited first, 9 of 9)

- [Challenges and Applications of Large Language Models](https://mlsanity.com/paper/2307.10169/) (2023)
- [Can ChatGPT Defend its Belief in Truth? Evaluating LLM Reasoning via Debate](https://mlsanity.com/paper/2305.13160/) (2023)
- [Spontaneous Reward Hacking in Iterative Self-Refinement](https://mlsanity.com/paper/2407.04549/) (2024)
- [An Empirical Categorization of Prompting Techniques for Large Language Models: A Practitioner's Guide](https://mlsanity.com/paper/2402.14837/) (2024)
- [Causality-Aided Trade-off Analysis for Machine Learning Fairness](https://mlsanity.com/paper/2305.13057/) (2023)
- [Moral Reasoning Across Languages: The Critical Role of Low-Resource Languages in LLMs](https://mlsanity.com/paper/2504.19759/) (2025)
- [How Toxic Can You Get? Search-based Toxicity Testing for Large Language Models](https://mlsanity.com/paper/2501.01741/) (2025)
- [Enhancing Illicit Activity Detection using XAI: A Multimodal Graph-LLM Framework](https://mlsanity.com/paper/2310.13787/) (2023)
- [Applying Standards to Advance Upstream & Downstream Ethics in Large Language Models](https://mlsanity.com/paper/2306.03503/) (2023)

## Abstract (arXiv)

As the popularity of large language models (LLMs) soars across various applications, ensuring their alignment with human values has become a paramount concern. In particular, given that LLMs have great potential to serve as general-purpose AI assistants in daily life, their subtly unethical suggestions become a serious and real concern. Tackling the challenge of automatically testing and repairing unethical suggestions is thus demanding. This paper introduces the first framework for testing and repairing unethical suggestions made by LLMs. We first propose ETHICSSUITE, a test suite that presents complex, contextualized, and realistic moral scenarios to test LLMs. We then propose a novel suggest-critic-reflect (SCR) process, serving as an automated test oracle to detect unethical suggestions. We recast deciding if LLMs yield unethical suggestions (a hard problem; often requiring human expertise and costly to decide) into a PCR task that can be automatically checked for violation. Moreover, we propose a novel on-the-fly (OTF) repairing scheme that repairs unethical suggestions made by LLMs in real-time. The OTF scheme is applicable to LLMs in a black-box API setting with moderate cost. With ETHICSSUITE, our study on seven popular LLMs (e.g., ChatGPT, GPT-4) uncovers in total 109,824 unethical suggestions. We apply our OTF scheme on two LLMs (Llama-13B and ChatGPT), which generates valid repair to a considerable amount of unethical ones, paving the way for more ethically conscious LLMs.