mlsanityData to 7 Oct 2026

A Survey on Responsible Generative AI: What to Generate and What Not

arXiv 2404.05783 ↗First posted 8 Apr 2024cs.CY cs.AI cs.CLcited by 8

Not on the map. Why?

Abstract (arXiv)

In recent years, generative AI (GenAI), like large language models and text-to-image models, has received significant attention across various domains. However, ensuring the responsible generation of content by these models is crucial for their real-world applicability. This raises an interesting question: What should responsible GenAI generate, and what should it not? To answer the question, this paper investigates the practical responsible requirements of both textual and visual generative models, outlining five key considerations: generating truthful content, avoiding toxic content, refusing harmful instruction, leaking no training data-related content, and ensuring generated content identifiable. Specifically, we review recent advancements and challenges in addressing these requirements. Besides, we discuss and emphasize the importance of responsible GenAI across healthcare, education, finance, and artificial general intelligence domains. Through a unified perspective on both textual and visual generative models, this paper aims to provide insights into practical safety-related issues and further benefit the community in building responsible GenAI.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 356 of its 607 references that are in the map. First posted on arXiv 8 Apr 2024.

Builds on

356 of 607 references.

References · 356

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  5. 2023GPT-4 Technical Reportcited by 18,132
  6. 2022Training language models to follow instructions with human feedbackcited by 15,712
  7. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  8. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  9. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  10. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  11. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  12. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
38 more
  1. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  2. 2013Intriguing properties of neural networkscited by 5,114
  3. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
  4. 2013Auto-Encoding Variational Bayescited by 3,980
  5. 2017Deep reinforcement learning from human preferencescited by 3,846
  6. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  7. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  8. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  9. 2016Improved Techniques for Training GANscited by 2,938
  10. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  11. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  12. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  13. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  14. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,388
  15. 2020The Pile: An 800GB Dataset of Diverse Text for Language Modelingcited by 2,346
  16. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  17. 2020Extracting Training Data from Large Language Modelscited by 2,144
  18. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
  19. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  20. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  21. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  22. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,696
  23. 2016Concrete Problems in AI Safetycited by 1,582
  24. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  25. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,565
  26. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  27. 2023Jailbreaking Black Box Large Language Models in Twenty Queriescited by 1,326
  28. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,259
  29. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,259
  30. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,235
  31. 2023Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversationscited by 1,124
  32. 2023Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!cited by 1,106
  33. 2023Kosmos-2: Grounding Multimodal Large Language Models to the Worldcited by 1,075
  34. 2023ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generationcited by 1,010
  35. 2023Towards Understanding Sycophancy in Language Modelscited by 988
  36. 2022Red Teaming Language Models with Language Modelscited by 983
  37. 2023Training Diffusion Models with Reinforcement Learningcited by 939
  38. 2023BloombergGPT: A Large Language Model for Financecited by 923

50 most cited of 356 All 356 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 4; 2026: 1.

8 papers.

  1. 2024Improved Techniques for Optimization-Based Jailbreaking on Large Language Modelscited by 98
  2. 2024Latent Guard: a Safety Framework for Text-to-image Generationcited by 68
  3. 2025ShieldGemma 2: Robust and Tractable Image Content Moderationcited by 27
  4. 2024How to Trace Latent Generative Model Generated Images without Artificial Watermark?cited by 25
  5. 2025SafeEditor: Unified MLLM for Efficient Post-hoc T2I Safety Editingcited by 2
  6. 2025Mind the Gap! Pathways Towards Unifying AI Safety and Ethics Researchcited by 2
  7. 2026Safe Autoregressive Image Generation with Iterative Self-Improving Codebookscited by 1
  8. 2025A Human-Centered Approach to Identifying Promises, Risks, & Challenges of Text-to-Image Generative AI in Radiologycited by 0