mlsanityData to 7 Oct 2026

Ethics Testing: Proactive Identification of Generative AI System Harms

arXiv 2604.22089 ↗First posted 23 Apr 2026cs.SE cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Generative Artificial Intelligence (GAI) systems that can automatically generate content in the form of source code or other contents (e.g., images) has seen increasing popularity due to the emergence of tools such as ChatGPT which rely on Large Language Models (LLMs). Misuse of the automatically generated content can incur serious consequences due to potential harms in the generated content. Despite the importance of ensuring the quality of automatically generated content, there is little to no approach that can systematically generate tests for identifying software harms in the content generated by these GAI systems. In this article, we introduce the novel concept of ethics testing which aims to systematically generate tests for identifying software harms. Different from existing testing methodologies (e.g., fairness testing that aims to identifying software discrimination), ethics testing aims to systematically detect software harms that could be induced due to unethical behavior (e.g., harmful behavior or behavior that violates intellectual property rights) in automatically generated content. We introduced the concept of ethics testing, discussed the challenges therewithin, and conducted five case studies to show how ethics testing can be performed for generative AI systems.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 42 of its 85 references that are in the map. First posted on arXiv 23 Apr 2026.

Builds on

42 of 85 references.

References · 42

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  5. 2022Red Teaming Language Models with Language Modelscited by 983
  6. 2021Ethical and social risks of harm from Language Modelscited by 957
  7. 2024Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attackscited by 450
  8. 2023Catastrophic Jailbreak of Open-source LLMs via Exploiting Generationcited by 439
  9. 2023GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Ciphercited by 401
  10. 2023Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructionscited by 377
  11. 2020Counterfactual VQA: A Cause-Effect Look at Language Biascited by 266
  12. 2023Certifying LLM Safety against Adversarial Promptingcited by 248
30 more
  1. 2021Challenges in Detoxifying Language Modelscited by 169
  2. 2020Recipes for Safety in Open-domain Chatbotscited by 168
  3. 2017Fairness Testing: Testing Software for Discriminationcited by 123
  4. 2020Model-Agnostic Counterfactual Reasoning for Eliminating Popularity Bias in Recommender Systemcited by 94
  5. 2021Bias in Machine Learning Software: Why? How? What to do?cited by 92
  6. 2024RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMscited by 89
  7. 2023Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicitycited by 86
  8. 2018Automated Directed Fairness Testingcited by 77
  9. 2022Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Modelscited by 67
  10. 2020Trustworthy AIcited by 62
  11. 2022Fairness Testing: A Comprehensive Survey and Analysis of Trendscited by 61
  12. 2024Investigating Bias in LLM-Based Bias Detection: Disparities between LLMs and Human Perceptioncited by 55
  13. 2023BiasAsker: Measuring the Bias in Conversational AI Systemcited by 52
  14. 2024ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluationcited by 46
  15. 2020Semantic Robustness of Models of Source Codecited by 43
  16. 2024The Ethics of Interaction: Mitigating Security Threats in LLMscited by 30
  17. 2022Worldwide AI Ethics: a review of 200 guidelines and recommendations for AI governancecited by 28
  18. 2024Multilingual Blending: LLM Safety Alignment Evaluation with Language Mixturecited by 22
  19. 2021BiasFinder: Metamorphic Test Generation to Uncover Bias for Sentiment Analysis Systemscited by 20
  20. 2024Breaking Bias, Building Bridges: Evaluation and Mitigation of Social Biases in LLMs via Contact Hypothesiscited by 19
  21. 2019Testing DNN Image Classifiers for Confusion & Bias Errorscited by 17
  22. 2021BiasRV: Uncovering Biased Sentiment Predictions at Runtimecited by 10
  23. 2021AI-Empowered Persuasive Video Generation: A Surveycited by 10
  24. 2024NeuFair: Neural Network Fairness Repair with Dropoutcited by 9
  25. 2024Evaluation Ethics of LLMs in Legal Domaincited by 8
  26. 2023Software Testing of Generative AI Systems: Challenges and Opportunitiescited by 6
  27. 2020A Benchmark Study of the Contemporary Toxicity Detectors on Software Engineering Interactionscited by 4
  28. 2023Exposing Algorithmic Discrimination and Its Consequences in Modern Society: Insights from a Scoping Studycited by 3
  29. 2024Understanding and Detecting Annotation-Induced Faults of Static Analyzerscited by 2
  30. 2022How heated is it? Understanding GitHub locked issuescited by 1

Built on by

Not cited yet.